feat(ui): canvas fullscreen toggle + keyboard tab navigation

The canvas header gains a fullscreen toggle (expands the panel to cover the
viewport; resize handle hidden while fullscreen). The artifact tab strip is now
a proper ARIA tablist with roving tabindex and Left/Right arrow-key navigation.

Assisted-by: Claude:claude-opus-4-8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

.agents/ds4-backend.md

@@ -44,6 +44,39 @@ maps to `DS4_THINK_HIGH`. We pass the chosen mode to `ds4_chat_append_assistant_
 via `ModelOptions.Options[] = "kv_cache_dir:/some/path"`. Format is **our own** -
 NOT bit-compatible with ds4-server's KVC files (interop is a follow-up plan).
 
+## Engine options (LoadModel)
+
+`LoadModel` maps `ModelOptions.Options[]` (`"key:value"`, from model-YAML
+`options:`) onto `ds4_engine_options` through a **declarative table**
+(`kEngineOptSpecs` + `apply_engine_option` in `grpc-server.cpp`). The struct is
+plain C with no reflection, so the field set is enumerated once in the table;
+adding a future engine knob is a one-line table row, not a new branch. Unknown
+keys are ignored (back-compat). A bare flag (`ssd_streaming` with no value)
+means `true`. Path-type values (`mtp_path`, `expert_profile_path`,
+`directional_steering_file`) resolve **relative to the model directory**, so a
+gallery entry can reference a companion file it downloaded by bare filename;
+absolute values pass through. `ds4_role` / `ds4_layers` / `ds4_listen` /
+`ds4_route_timeout` / `kv_cache_dir` keep their dedicated handling (validation
++ coordinator wiring) and are not in the table.
+
+Wired keys: `mtp_path`, `mtp_draft`, `mtp_margin`, `prefill_chunk`,
+`power_percent`, `warm_weights`, `quality`, `ssd_streaming`,
+`ssd_streaming_cold`, `ssd_streaming_preload_experts`,
+`ssd_streaming_cache_experts` (count or `NGB`, sets both experts+bytes via
+`ds4_parse_streaming_cache_experts_arg`), `simulate_used_memory` (`NGB` via
+`ds4_parse_gib_arg`), `expert_profile_path`, `directional_steering_file`,
+`directional_steering_attn`, `directional_steering_ffn`.
+
+## SSD streaming (running models larger than RAM)
+
+ds4's **SSD streaming** keeps non-routed weights resident and streams routed MoE
+experts from the GGUF on cache misses, turning "does it fit in RAM" into a speed
+spectrum. **Metal (Darwin) only** - it is a no-op on CUDA/CPU. Enable with
+`options: ["ssd_streaming"]`; size the routed-expert cache with
+`ssd_streaming_cache_experts:NGB` (omit for ds4's automatic 80%-of-working-set
+budget). Gallery entries built on this: `deepseek-v4-flash-q4-ssd` (153 GB Flash
+on a 128 GB Mac) and `deepseek-v4-pro-q2-ssd` (433 GB Pro, experimental).
+
 ## Build matrix
 
 | Build | Where | Notes |

.dockerignore

@@ -31,6 +31,15 @@ backend/python/**/source
 backend/cpp/llama-cpp/llama.cpp
 backend/cpp/llama-cpp-*-build
 
+# privacy-filter: same in-place pattern. The Makefile fetches privacy-filter.cpp
+# at the pinned commit (or symlinks a PRIVACY_FILTER_SRC checkout for local dev).
+# A stale dir/symlink COPY'd into the image makes the clone step fail (dangling
+# symlink) or compile against the wrong commit, so keep host build state out.
+backend/cpp/privacy-filter/privacy-filter.cpp
+backend/cpp/privacy-filter/build
+backend/cpp/privacy-filter/grpc-server
+backend/cpp/privacy-filter/package
+
 # Rust backend build output (sources are tracked; target/ is generated)
 backend/rust/*/target
 

.github/backend-matrix.yml

@@ -716,6 +716,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "8"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-12-depth-anything-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'cublas'
     cuda-major-version: "12"
     cuda-minor-version: "8"
@@ -781,6 +794,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "8"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-12-omnivoice-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "omnivoice-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'cublas'
     cuda-major-version: "12"
     cuda-minor-version: "8"
@@ -1569,6 +1595,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-13-depth-anything-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'cublas'
     cuda-major-version: "13"
     cuda-minor-version: "0"
@@ -1608,6 +1647,19 @@ include:
     backend: "locate-anything-cpp"
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-cuda-13-arm64-depth-anything-cpp'
+    base-image: "ubuntu:24.04"
+    ubuntu-version: '2404'
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
   - build-type: 'cublas'
     cuda-major-version: "13"
     cuda-minor-version: "0"
@@ -1712,6 +1764,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-13-omnivoice-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "omnivoice-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'cublas'
     cuda-major-version: "13"
     cuda-minor-version: "0"
@@ -1751,6 +1816,19 @@ include:
     backend: "qwen3-tts-cpp"
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-cuda-13-arm64-omnivoice-cpp'
+    base-image: "ubuntu:24.04"
+    ubuntu-version: '2404'
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "omnivoice-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
   - build-type: 'cublas'
     cuda-major-version: "13"
     cuda-minor-version: "0"
@@ -2592,6 +2670,78 @@ include:
     dockerfile: "./backend/Dockerfile.ds4"
     context: "./"
     ubuntu-version: '2404'
+  # privacy-filter: PII/NER token classifier (per-arch native -> manifest merge).
+  # Every variant builds FROM a prebuilt quay.io/go-skynet/ci-cache:base-grpc-*
+  # image (gRPC + cmake + protoc + conditional CUDA/Vulkan already installed),
+  # exactly like llama-cpp — no toolchain is installed in Dockerfile.privacy-filter.
+  # builder-base-image makes the workflow use the Dockerfile's builder-prebuilt
+  # stage; without it (local builds) the builder-fromsource stage runs the same
+  # .docker/install-base-deps.sh.
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-privacy-filter'
+    builder-base-image: 'quay.io/go-skynet/ci-cache:base-grpc-amd64'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'true'
+    backend: "privacy-filter"
+    dockerfile: "./backend/Dockerfile.privacy-filter"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-privacy-filter'
+    builder-base-image: 'quay.io/go-skynet/ci-cache:base-grpc-arm64'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'true'
+    backend: "privacy-filter"
+    dockerfile: "./backend/Dockerfile.privacy-filter"
+    context: "./"
+    ubuntu-version: '2404'
+  # Vulkan: base-grpc-vulkan-amd64 carries the SDK. arm64 vulkan is a one-line
+  # add once amd64 is proven in CI.
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-privacy-filter'
+    builder-base-image: 'quay.io/go-skynet/ci-cache:base-grpc-vulkan-amd64'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "privacy-filter"
+    dockerfile: "./backend/Dockerfile.privacy-filter"
+    context: "./"
+    ubuntu-version: '2404'
+  # CUDA: base-grpc-cuda-13-amd64 carries the toolkit; BUILD_TYPE=cublas ->
+  # -DPF_CUDA=ON. cuda-12 and arm64/l4t are one-line adds once cuda-13 amd64 is
+  # proven in CI.
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-13-privacy-filter'
+    builder-base-image: 'quay.io/go-skynet/ci-cache:base-grpc-cuda-13-amd64'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'true'
+    backend: "privacy-filter"
+    dockerfile: "./backend/Dockerfile.privacy-filter"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: ''
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -2859,6 +3009,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-depth-anything-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'sycl_f32'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -2872,6 +3035,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'sycl_f32'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f32-depth-anything-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'sycl_f16'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -2885,6 +3061,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'sycl_f16'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f16-depth-anything-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'vulkan'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -2899,6 +3088,20 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-depth-anything-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'vulkan'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -2913,6 +3116,20 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-depth-anything-cpp'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'sycl_f32'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -3019,6 +3236,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2204'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-arm64-depth-anything-cpp'
+    base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2204'
   # whisper
   - build-type: ''
     cuda-major-version: ""
@@ -3483,6 +3713,35 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  # omnivoice-cpp
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-omnivoice-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "omnivoice-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-omnivoice-cpp'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "omnivoice-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'sycl_f32'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -3496,6 +3755,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'sycl_f32'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f32-omnivoice-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "omnivoice-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'sycl_f16'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -3509,6 +3781,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'sycl_f16'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f16-omnivoice-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "omnivoice-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'vulkan'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -3523,6 +3808,20 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-omnivoice-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "omnivoice-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'vulkan'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -3537,6 +3836,20 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-omnivoice-cpp'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "omnivoice-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'cublas'
     cuda-major-version: "12"
     cuda-minor-version: "0"
@@ -3550,6 +3863,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2204'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-arm64-omnivoice-cpp'
+    base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "omnivoice-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2204'
   - build-type: 'hipblas'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -3563,6 +3889,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'hipblas'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-rocm-hipblas-omnivoice-cpp'
+    base-image: "rocm/dev-ubuntu-24.04:6.4.4"
+    runs-on: 'ubuntu-latest'
+    skip-drivers: 'false'
+    backend: "omnivoice-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   # vibevoice-cpp
   - build-type: ''
     cuda-major-version: ""
@@ -4342,6 +4681,36 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  # supertonic CPU (amd64)
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-supertonic'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "supertonic"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  # supertonic CPU (arm64)
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-supertonic'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "supertonic"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
 
 # Darwin matrix (consumed by backend-jobs-darwin).
 includeDarwin:
@@ -4393,6 +4762,10 @@ includeDarwin:
     tag-suffix: "-metal-darwin-arm64-qwen3-tts-cpp"
     build-type: "metal"
     lang: "go"
+  - backend: "omnivoice-cpp"
+    tag-suffix: "-metal-darwin-arm64-omnivoice-cpp"
+    build-type: "metal"
+    lang: "go"
   - backend: "vibevoice-cpp"
     tag-suffix: "-metal-darwin-arm64-vibevoice-cpp"
     build-type: "metal"
@@ -4475,3 +4848,6 @@ includeDarwin:
   - backend: "speaker-recognition"
     tag-suffix: "-metal-darwin-arm64-speaker-recognition"
     build-type: "mps"
+  - backend: "ds4"
+    tag-suffix: "-metal-darwin-arm64-ds4"
+    lang: "go"

.github/workflows/backend_build_darwin.yml

@@ -98,6 +98,7 @@ jobs:
             /opt/homebrew/Cellar/hiredis
             /opt/homebrew/Cellar/xxhash
             /opt/homebrew/Cellar/zstd
+            /opt/homebrew/Cellar/nlohmann-json
           key: brew-${{ runner.os }}-${{ runner.arch }}-v1-${{ hashFiles('.github/workflows/backend_build_darwin.yml') }}
 
       - name: Dependencies
@@ -109,7 +110,10 @@ jobs:
           # Without explicitly installing them, a brew cache-hit run restores
           # ccache's Cellar dir but skips installing those transitive deps,
           # and ccache fails at runtime with `dyld: Library not loaded`.
-          brew install protobuf grpc make protoc-gen-go protoc-gen-go-grpc libomp llvm ccache blake3 fmt hiredis xxhash zstd
+          # nlohmann-json is header-only and required by the ds4 backend
+          # (dsml_renderer.cpp includes <nlohmann/json.hpp>); on Linux it comes
+          # from the apt-installed nlohmann-json3-dev in the build image.
+          brew install protobuf grpc make protoc-gen-go protoc-gen-go-grpc libomp llvm ccache blake3 fmt hiredis xxhash zstd nlohmann-json
           # Force-reinstall ccache so brew re-validates its full runtime-dep
           # closure on every run. This is the durable fix: when the upstream
           # ccache formula gains a new transitive dep (as it has multiple times
@@ -128,7 +132,7 @@ jobs:
           # and decides "already installed" without re-linking, so on a cache-
           # hit run the formulas aren't on PATH. Force-link them; --overwrite
           # tolerates pre-existing symlinks from earlier installs.
-          brew link --overwrite protobuf grpc make protoc-gen-go protoc-gen-go-grpc libomp llvm ccache blake3 fmt hiredis xxhash zstd 2>/dev/null || true
+          brew link --overwrite protobuf grpc make protoc-gen-go protoc-gen-go-grpc libomp llvm ccache blake3 fmt hiredis xxhash zstd nlohmann-json 2>/dev/null || true
 
       - name: Save Homebrew cache
         if: github.event_name != 'pull_request' && steps.brew-cache.outputs.cache-hit != 'true'
@@ -148,6 +152,7 @@ jobs:
             /opt/homebrew/Cellar/hiredis
             /opt/homebrew/Cellar/xxhash
             /opt/homebrew/Cellar/zstd
+            /opt/homebrew/Cellar/nlohmann-json
           key: brew-${{ runner.os }}-${{ runner.arch }}-v1-${{ hashFiles('.github/workflows/backend_build_darwin.yml') }}
 
       # ---- ccache for llama.cpp CMake builds ----

.github/workflows/bump_deps.yaml

@@ -26,6 +26,10 @@ jobs:
             variable: "DS4_VERSION"
             branch: "main"
             file: "backend/cpp/ds4/Makefile"
+          - repository: "localai-org/privacy-filter.cpp"
+            variable: "PRIVACY_FILTER_VERSION"
+            branch: "master"
+            file: "backend/cpp/privacy-filter/Makefile"
           - repository: "ggml-org/whisper.cpp"
             variable: "WHISPER_CPP_VERSION"
             branch: "master"
@@ -38,6 +42,10 @@ jobs:
             variable: "PARAKEET_VERSION"
             branch: "master"
             file: "backend/go/parakeet-cpp/Makefile"
+          - repository: "mudler/depth-anything.cpp"
+            variable: "DEPTHANYTHING_VERSION"
+            branch: "master"
+            file: "backend/go/depth-anything-cpp/Makefile"
           - repository: "leejet/stable-diffusion.cpp"
             variable: "STABLEDIFFUSION_GGML_VERSION"
             branch: "master"
@@ -66,10 +74,14 @@ jobs:
             variable: "LOCATEANYTHING_VERSION"
             branch: "master"
             file: "backend/go/locate-anything-cpp/Makefile"
-          - repository: "predict-woo/qwen3-tts.cpp"
+          - repository: "ServeurpersoCom/qwentts.cpp"
             variable: "QWEN3TTS_CPP_VERSION"
-            branch: "main"
+            branch: "master"
             file: "backend/go/qwen3-tts-cpp/Makefile"
+          - repository: "ServeurpersoCom/omnivoice.cpp"
+            variable: "OMNIVOICE_VERSION"
+            branch: "master"
+            file: "backend/go/omnivoice-cpp/Makefile"
           - repository: "localai-org/vibevoice.cpp"
             variable: "VIBEVOICE_CPP_VERSION"
             branch: "master"

.github/workflows/secscan.yaml

@@ -21,7 +21,10 @@ jobs:
         uses: securego/gosec@v2.27.1
         with:
           # we let the report trigger content trigger a failure using the GitHub Security features.
-          args: '-no-fail -fmt sarif -out results.sarif ./...'
+          # backend/go/supertonic is excluded: it vendors upstream supertone-inc/supertonic
+          # (helper.go), whose findings (G304 model-file loads, G404 math/rand for flow-matching
+          # noise, G104 unhandled errors) are inherent to that upstream code, not ours to rewrite.
+          args: '-no-fail -exclude-dir=backend/go/supertonic -fmt sarif -out results.sarif ./...'
       - name: Upload SARIF file
         if: ${{ github.actor != 'dependabot[bot]' }}
         uses: github/codeql-action/upload-sarif@v4

.golangci.yml

@@ -74,6 +74,8 @@ linters:
     paths:
       # Upstream whisper.cpp source tree fetched by the whisper backend Makefile.
       - 'backend/go/whisper/sources'
+      # Vendored upstream supertonic pipeline (supertone-inc/supertonic go/helper.go).
+      - 'backend/go/supertonic/helper.go'
       - 'docs/'
     rules:
       # CLI entry points: kong's `env:"..."` tag is the legitimate env→struct

Makefile

@@ -1,5 +1,5 @@
 # Disable parallel execution for backend builds
-.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/turboquant backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/crispasr backends/parakeet-cpp backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/rfdetr-cpp backends/insightface backends/speaker-recognition backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/sglang backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral backends/opus backends/trl backends/llama-cpp-quantization backends/kokoros backends/sam3-cpp backends/qwen3-tts-cpp backends/vibevoice-cpp backends/localvqe backends/tinygrad backends/sherpa-onnx backends/ds4 backends/ds4-darwin backends/liquid-audio
+.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/turboquant backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/crispasr backends/parakeet-cpp backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/rfdetr-cpp backends/insightface backends/speaker-recognition backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/sglang backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral backends/opus backends/trl backends/llama-cpp-quantization backends/kokoros backends/sam3-cpp backends/qwen3-tts-cpp backends/omnivoice-cpp backends/vibevoice-cpp backends/localvqe backends/tinygrad backends/sherpa-onnx backends/ds4 backends/ds4-darwin backends/liquid-audio backends/supertonic backends/depth-anything-cpp backends/privacy-filter
 
 GOCMD=go
 GOTEST=$(GOCMD) test
@@ -595,6 +595,8 @@ test-extra: prepare-test-extra
 	$(MAKE) -C backend/rust/kokoros test
 	$(MAKE) -C backend/go/rfdetr-cpp test
 	$(MAKE) -C backend/go/locate-anything-cpp test
+	$(MAKE) -C backend/go/depth-anything-cpp test
+	$(MAKE) -C backend/go/supertonic test
 
 ##
 ## End-to-end gRPC tests that exercise a built backend container image.
@@ -1162,6 +1164,10 @@ BACKEND_TURBOQUANT = turboquant|turboquant|.|false|false
 # Single-model; hardware-only validation lives at tests/e2e-backends/
 # (BACKEND_BINARY mode); see docs/superpowers/plans/2026-05-11-ds4-backend.md.
 BACKEND_DS4 = ds4|ds4|.|false|false
+# privacy-filter wraps the standalone privacy-filter.cpp GGML engine (the
+# openai-privacy-filter PII/NER token classifier) — the TokenClassify RPC for
+# the PII redactor tier, on stock ggml with no llama.cpp carry-patches.
+BACKEND_PRIVACY_FILTER = privacy-filter|privacy-filter|.|false|false
 
 # Golang backends
 BACKEND_PIPER = piper|golang|.|false|true
@@ -1173,13 +1179,16 @@ BACKEND_STABLEDIFFUSION_GGML = stablediffusion-ggml|golang|.|--progress=plain|tr
 BACKEND_WHISPER = whisper|golang|.|false|true
 BACKEND_CRISPASR = crispasr|golang|.|false|true
 BACKEND_PARAKEET_CPP = parakeet-cpp|golang|.|false|true
+BACKEND_DEPTH_ANYTHING_CPP = depth-anything-cpp|golang|.|false|true
 BACKEND_VOXTRAL = voxtral|golang|.|false|true
 BACKEND_ACESTEP_CPP = acestep-cpp|golang|.|false|true
 BACKEND_QWEN3_TTS_CPP = qwen3-tts-cpp|golang|.|false|true
+BACKEND_OMNIVOICE_CPP = omnivoice-cpp|golang|.|false|true
 BACKEND_VIBEVOICE_CPP = vibevoice-cpp|golang|.|false|true
 BACKEND_LOCALVQE = localvqe|golang|.|false|true
 BACKEND_OPUS = opus|golang|.|false|true
 BACKEND_SHERPA_ONNX = sherpa-onnx|golang|.|false|true
+BACKEND_SUPERTONIC = supertonic|golang|.|false|true
 
 # Python backends with root context
 BACKEND_RERANKERS = rerankers|python|.|false|true
@@ -1253,6 +1262,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_LLAMA_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_IK_LLAMA_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_TURBOQUANT)))
 $(eval $(call generate-docker-build-target,$(BACKEND_DS4)))
+$(eval $(call generate-docker-build-target,$(BACKEND_PRIVACY_FILTER)))
 $(eval $(call generate-docker-build-target,$(BACKEND_PIPER)))
 $(eval $(call generate-docker-build-target,$(BACKEND_LOCAL_STORE)))
 $(eval $(call generate-docker-build-target,$(BACKEND_CLOUD_PROXY)))
@@ -1262,6 +1272,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_STABLEDIFFUSION_GGML)))
 $(eval $(call generate-docker-build-target,$(BACKEND_WHISPER)))
 $(eval $(call generate-docker-build-target,$(BACKEND_CRISPASR)))
 $(eval $(call generate-docker-build-target,$(BACKEND_PARAKEET_CPP)))
+$(eval $(call generate-docker-build-target,$(BACKEND_DEPTH_ANYTHING_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_VOXTRAL)))
 $(eval $(call generate-docker-build-target,$(BACKEND_OPUS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_RERANKERS)))
@@ -1294,6 +1305,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_WHISPERX)))
 $(eval $(call generate-docker-build-target,$(BACKEND_ACE_STEP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_ACESTEP_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_QWEN3_TTS_CPP)))
+$(eval $(call generate-docker-build-target,$(BACKEND_OMNIVOICE_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_VIBEVOICE_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_LOCALVQE)))
 $(eval $(call generate-docker-build-target,$(BACKEND_MLX)))
@@ -1306,12 +1318,13 @@ $(eval $(call generate-docker-build-target,$(BACKEND_KOKOROS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_SAM3_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_RFDETR_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_SHERPA_ONNX)))
+$(eval $(call generate-docker-build-target,$(BACKEND_SUPERTONIC)))
 
 # Pattern rule for docker-save targets
 docker-save-%: backend-images
 	docker save local-ai-backend:$* -o backend-images/$*.tar
 
-docker-build-backends: docker-build-llama-cpp docker-build-ik-llama-cpp docker-build-turboquant docker-build-ds4 docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-sglang docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-crispasr docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-liquid-audio docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-fish-speech docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-acestep-cpp docker-build-voxtral docker-build-mlx-distributed docker-build-trl docker-build-llama-cpp-quantization docker-build-tinygrad docker-build-kokoros docker-build-sam3-cpp docker-build-rfdetr-cpp docker-build-qwen3-tts-cpp docker-build-vibevoice-cpp docker-build-localvqe docker-build-insightface docker-build-speaker-recognition docker-build-sherpa-onnx docker-build-cloud-proxy
+docker-build-backends: docker-build-llama-cpp docker-build-ik-llama-cpp docker-build-turboquant docker-build-ds4 docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-sglang docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-crispasr docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-liquid-audio docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-fish-speech docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-acestep-cpp docker-build-voxtral docker-build-mlx-distributed docker-build-trl docker-build-llama-cpp-quantization docker-build-tinygrad docker-build-kokoros docker-build-sam3-cpp docker-build-rfdetr-cpp docker-build-qwen3-tts-cpp docker-build-omnivoice-cpp docker-build-vibevoice-cpp docker-build-localvqe docker-build-insightface docker-build-speaker-recognition docker-build-sherpa-onnx docker-build-cloud-proxy docker-build-supertonic docker-build-depth-anything-cpp docker-build-privacy-filter
 
 ########################################################
 ### Mock Backend for E2E Tests

README.md

@@ -29,6 +29,18 @@
 <a href="https://trendshift.io/repositories/5539" target="_blank"><img src="https://trendshift.io/api/badge/repositories/5539" alt="mudler%2FLocalAI | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 </p>
 
+<!-- Keep these links, translations synced daily. -->
+<p align="center">
+<a href="https://zdoc.app/de/mudler/LocalAI">Deutsch</a> |
+<a href="https://zdoc.app/es/mudler/LocalAI">Español</a> |
+<a href="https://zdoc.app/fr/mudler/LocalAI">français</a> |
+<a href="https://zdoc.app/ja/mudler/LocalAI">日本語</a> |
+<a href="https://zdoc.app/ko/mudler/LocalAI">한국어</a> |
+<a href="https://zdoc.app/pt/mudler/LocalAI">Português</a> |
+<a href="https://zdoc.app/ru/mudler/LocalAI">Русский</a> |
+<a href="https://zdoc.app/zh/mudler/LocalAI">中文</a>
+</p>
+
 **LocalAI** is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
 
 **A small core, not a bundle.** Each backend wraps a best-in-class engine (llama.cpp, vLLM, whisper.cpp, stable-diffusion, MLX...) in its own image, pulled only when a model needs it. You install nothing you don't use.
@@ -165,6 +177,10 @@ For more details, see the [Getting Started guide](https://localai.io/basics/gett
 
 ## Latest News
 
+- **June 2026**: New [realtime voice assistant demo](https://github.com/localai-org/localai-realtime-demo) (a tiny Go client for the Realtime API with a full talk-back voice loop and tool calling), plus [streaming of the realtime LLM / TTS / transcription pipeline stages](https://github.com/mudler/LocalAI/pull/10176) and [configurable WebRTC ICE candidates](https://github.com/mudler/LocalAI/pull/10231).
+- **June 2026**: Big speech push: the [parakeet.cpp](https://github.com/mudler/parakeet.cpp) ASR engine gains [NeMo-faithful segment timestamps](https://github.com/mudler/LocalAI/pull/10207), a [multilingual streaming Nemotron-3.5 model](https://github.com/mudler/LocalAI/pull/10199), [dynamic batching for concurrent transcription](https://github.com/mudler/LocalAI/pull/10112) and [CUDA graphs](https://github.com/mudler/LocalAI/pull/10273); the new [CrispASR backend](https://github.com/mudler/LocalAI/pull/10099) adds multi-architecture ASR + TTS, and [60 Piper TTS voices across 42 languages](https://github.com/mudler/LocalAI/pull/10296) land in the gallery (plus [per-request TTS instructions and params](https://github.com/mudler/LocalAI/pull/10172)).
+- **June 2026**: New backends and models: [locate-anything.cpp](https://github.com/mudler/LocalAI/pull/10264) for open-vocabulary object detection via ggml, [Ideogram4 image generation](https://github.com/mudler/LocalAI/pull/10201) in stablediffusion-ggml, [llama.cpp video input](https://github.com/mudler/LocalAI/pull/10216), and the [Gemma 4 QAT family with MTP speculative-decoding pairs](https://github.com/mudler/LocalAI/pull/10215). Plus an [interactive CLI chat mode](https://github.com/mudler/LocalAI/pull/10226) and [RAG source citations in agent responses](https://github.com/mudler/LocalAI/pull/10228).
+- **June 2026**: Distributed mode hardening: [prefix-cache-aware routing](https://github.com/mudler/LocalAI/pull/10071), a [production-ready request router with auto-sized embedding/rerank batches](https://github.com/mudler/LocalAI/pull/10104), [ds4 layer-split distributed inference](https://github.com/mudler/LocalAI/pull/10098), [NATS JWT auth + TLS/mTLS](https://github.com/mudler/LocalAI/pull/10159), and [resumable file uploads](https://github.com/mudler/LocalAI/pull/10109).
 - **May 2026**: **LocalAI 4.3.0** - `llama.cpp` [prompt cache on by default](https://github.com/mudler/LocalAI/pull/9925) (repeated system prompts collapse from minutes to seconds), [keyless cosign signing of backend OCI images](https://github.com/mudler/LocalAI/pull/9823), [per-API-key + per-user usage attribution](https://github.com/mudler/LocalAI/pull/9920), Distributed v3 with [per-request replica routing](https://github.com/mudler/LocalAI/pull/9968). [Release notes](https://github.com/mudler/LocalAI/releases/tag/v4.3.0)
 - **May 2026**: **LocalAI 4.2.0** - LocalAI sees and hears: [voice recognition](https://github.com/mudler/LocalAI/pull/9500), [face recognition + antispoofing liveness](https://github.com/mudler/LocalAI/pull/9480), speaker diarization. Plus [drop-in Ollama API](https://github.com/mudler/LocalAI/pull/9284), [video generation](https://github.com/mudler/LocalAI/pull/9420), redesigned UI with i18n + admin-configurable branding, vLLM at feature parity with llama.cpp, and 11 new backends. [Release notes](https://github.com/mudler/LocalAI/releases/tag/v4.2.0)
 - **April 2026**: **LocalAI 4.1.0** - LocalAI becomes a control tower: distributed cluster mode with VRAM-aware smart routing + autoscaling, multi-user platform with OIDC and API keys, per-user quotas with predictive analytics, in-UI fine-tuning with TRL (auto-export to GGUF), on-the-fly quantization backend, visual pipeline editor. [Release notes](https://github.com/mudler/LocalAI/releases/tag/v4.1.0)
@@ -204,10 +220,26 @@ For older news and full release notes, see [GitHub Releases](https://github.com/
 
 ## Supported Backends & Acceleration
 
-LocalAI supports **36+ backends** including llama.cpp, vLLM, transformers, whisper.cpp, diffusers, MLX, MLX-VLM, and many more. Hardware acceleration is available for **NVIDIA** (CUDA 12/13), **AMD** (ROCm), **Intel** (oneAPI/SYCL), **Apple Silicon** (Metal), **Vulkan**, and **NVIDIA Jetson** (L4T). All backends can be installed on-the-fly from the [Backend Gallery](https://localai.io/backends/).
+LocalAI supports **60+ backends** including llama.cpp, vLLM, SGLang, transformers, whisper.cpp, diffusers, MLX, MLX-VLM, and many more. Hardware acceleration is available for **NVIDIA** (CUDA 12/13), **AMD** (ROCm), **Intel** (oneAPI/SYCL), **Apple Silicon** (Metal), **Vulkan**, and **NVIDIA Jetson** (L4T). All backends can be installed on-the-fly from the [Backend Gallery](https://localai.io/backends/).
 
 See the full [Backend & Model Compatibility Table](https://localai.io/model-compatibility/) and [GPU Acceleration guide](https://localai.io/features/gpu-acceleration/).
 
+### Backends built by us
+
+Most backends wrap a best-in-class upstream engine. A handful of them are native C/C++/GGML engines (no Python at inference) developed and maintained by the LocalAI project itself:
+
+| Backend | What it does |
+|---------|-------------|
+| [parakeet.cpp](https://github.com/mudler/parakeet.cpp) | C++/GGML port of NVIDIA NeMo Parakeet ASR (tdt/ctc/rnnt/hybrid), with cache-aware streaming transcription |
+| [voxtral.c](https://github.com/mudler/voxtral.c) | Voxtral Realtime 4B speech-to-text in pure C |
+| [vibevoice.cpp](https://github.com/mudler/vibevoice.cpp) | Native port of Microsoft VibeVoice for TTS (voice cloning) and long-form ASR with speaker diarization |
+| [rf-detr.cpp](https://github.com/mudler/rf-detr.cpp) | Native RF-DETR object detection and instance segmentation |
+| [locate-anything.cpp](https://github.com/mudler/locate-anything.cpp) | Open-vocabulary object detection and visual grounding (LocateAnything-3B) |
+| [depth-anything.cpp](https://github.com/mudler/depth-anything.cpp) | Depth Anything 3 monocular metric depth + camera pose estimation |
+| [privacy-filter.cpp](https://github.com/localai-org/privacy-filter.cpp) | Standalone GGML PII/NER token-classification engine powering LocalAI's PII redaction tier |
+| [LocalVQE](https://github.com/localai-org/LocalVQE) | Joint acoustic echo cancellation, noise suppression, and dereverberation |
+| [local-store](https://github.com/mudler/LocalAI) | Local-first vector database for embeddings (shipped in-tree) |
+
 ## Resources
 
 - [Documentation](https://localai.io/)
@@ -217,7 +249,7 @@ See the full [Backend & Model Compatibility Table](https://localai.io/model-comp
 - [Integrations & community projects](https://localai.io/docs/integrations/)
 - [Installation video walkthrough](https://www.youtube.com/watch?v=cMVNnlqwfw4)
 - [Media & blog posts](https://localai.io/basics/news/#media-blogs-social)
-- [Examples](https://github.com/mudler/LocalAI-examples)
+- [Examples](https://github.com/mudler/LocalAI-examples) — including the [realtime voice assistant demo](https://github.com/localai-org/localai-realtime-demo) (Go client for the Realtime API with tool calling)
 
 ## Team
 

backend/Dockerfile.privacy-filter

@@ -0,0 +1,109 @@
+ARG BASE_IMAGE=ubuntu:24.04
+# BUILDER_BASE_IMAGE defaults to BASE_IMAGE so the Dockerfile parses when no
+# prebuilt base is supplied; the builder-prebuilt stage is only entered when
+# BUILDER_TARGET=builder-prebuilt, so the fallback content is harmless
+# (BuildKit prunes the unreferenced builder).
+ARG BUILDER_BASE_IMAGE=${BASE_IMAGE}
+# BUILDER_TARGET selects which builder stage the scratch image copies from.
+# Declared before any FROM so it is usable in `FROM ${BUILDER_TARGET}`. The
+# backend_build workflow sets it to builder-prebuilt when the matrix entry
+# provides builder-base-image, else builder-fromsource (the local default).
+ARG BUILDER_TARGET=builder-fromsource
+ARG APT_MIRROR=""
+ARG APT_PORTS_MIRROR=""
+
+# privacy-filter: standalone GGML engine for the openai-privacy-filter PII/NER
+# token classifier, wrapped as a LocalAI gRPC backend.
+#
+# Mirrors backend/Dockerfile.llama-cpp: the build toolchain (gRPC + cmake +
+# protoc + conditional CUDA/Vulkan) comes from the shared
+# .docker/install-base-deps.sh (from-source path) or a prebuilt
+# quay.io/go-skynet/ci-cache:base-grpc-* image (CI path) — nothing GPU-specific
+# is hand-rolled here. BUILD_TYPE selects the engine backend in the Makefile:
+# "" = cpu, "cublas" -> -DPF_CUDA=ON, "vulkan" -> -DPF_VULKAN=ON.
+
+# ============================================================================
+# Stage: builder-fromsource — self-contained build. Runs the same install
+# script backend/Dockerfile.base-grpc-builder runs, so this path is
+# bit-equivalent to the prebuilt base. Used when BUILDER_TARGET=builder-fromsource
+# (the default; local `make backends/privacy-filter`).
+# ============================================================================
+FROM ${BASE_IMAGE} AS builder-fromsource
+ARG BUILD_TYPE
+ARG CUDA_MAJOR_VERSION
+ARG CUDA_MINOR_VERSION
+ARG CMAKE_FROM_SOURCE=false
+# CUDA Toolkit 13.x needs CMake 3.31.9+ for correct toolchain/arch detection.
+ARG CMAKE_VERSION=3.31.10
+ARG GRPC_VERSION=v1.65.0
+ARG GRPC_MAKEFLAGS="-j4 -Otarget"
+ARG SKIP_DRIVERS=false
+ARG TARGETARCH
+ARG UBUNTU_VERSION=2404
+ARG APT_MIRROR
+ARG APT_PORTS_MIRROR
+
+ENV BUILD_TYPE=${BUILD_TYPE} \
+    CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} \
+    CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION} \
+    CMAKE_FROM_SOURCE=${CMAKE_FROM_SOURCE} \
+    CMAKE_VERSION=${CMAKE_VERSION} \
+    GRPC_VERSION=${GRPC_VERSION} \
+    GRPC_MAKEFLAGS=${GRPC_MAKEFLAGS} \
+    SKIP_DRIVERS=${SKIP_DRIVERS} \
+    TARGETARCH=${TARGETARCH} \
+    UBUNTU_VERSION=${UBUNTU_VERSION} \
+    APT_MIRROR=${APT_MIRROR} \
+    APT_PORTS_MIRROR=${APT_PORTS_MIRROR} \
+    DEBIAN_FRONTEND=noninteractive
+# CUDA on PATH (a no-op when CUDA is not installed, e.g. cpu/vulkan builds).
+ENV PATH=/usr/local/cuda/bin:${PATH}
+
+WORKDIR /build
+
+# apt deps + cmake + protoc + gRPC + conditional CUDA/Vulkan, all from the
+# shared script (the source of truth that base-grpc-builder also runs).
+RUN --mount=type=bind,source=.docker/install-base-deps.sh,target=/usr/local/sbin/install-base-deps \
+    --mount=type=bind,source=.docker/apt-mirror.sh,target=/usr/local/sbin/apt-mirror \
+    bash /usr/local/sbin/install-base-deps
+
+# install-base-deps installs gRPC under /opt/grpc; copy it to /usr/local so the
+# backend's find_package(gRPC CONFIG) resolves it at the canonical prefix.
+RUN cp -a /opt/grpc/. /usr/local/
+
+COPY . /LocalAI
+
+RUN --mount=type=cache,target=/root/.ccache,id=privacy-filter-ccache-${TARGETARCH}-${BUILD_TYPE},sharing=locked \
+    make -C /LocalAI/backend/cpp/privacy-filter BUILD_TYPE=${BUILD_TYPE} NATIVE=false grpc-server package
+
+# ============================================================================
+# Stage: builder-prebuilt — FROM a prebuilt
+# quay.io/go-skynet/ci-cache:base-grpc-* image (gRPC at /opt/grpc + apt deps +
+# CUDA/Vulkan already installed). Used in CI when the matrix entry sets
+# builder-base-image.
+# ============================================================================
+FROM ${BUILDER_BASE_IMAGE} AS builder-prebuilt
+ARG BUILD_TYPE
+ARG TARGETARCH
+ENV BUILD_TYPE=${BUILD_TYPE}
+# CUDA on PATH (a no-op for the cpu/vulkan base images).
+ENV PATH=/usr/local/cuda/bin:${PATH}
+
+# Mirror builder-fromsource: the base-grpc image installs gRPC to /opt/grpc but
+# does not copy it to /usr/local.
+RUN cp -a /opt/grpc/. /usr/local/
+
+COPY . /LocalAI
+
+RUN --mount=type=cache,target=/root/.ccache,id=privacy-filter-ccache-${TARGETARCH}-${BUILD_TYPE},sharing=locked \
+    make -C /LocalAI/backend/cpp/privacy-filter BUILD_TYPE=${BUILD_TYPE} NATIVE=false grpc-server package
+
+# ============================================================================
+# Final stage — copy the package output from the selected builder. BuildKit
+# does not expand variables in `COPY --from=`, so alias the chosen builder to a
+# fixed stage name first.
+# ============================================================================
+FROM ${BUILDER_TARGET} AS builder
+
+FROM scratch
+COPY --from=builder /LocalAI/backend/cpp/privacy-filter/package/. ./

backend/backend.proto

@@ -24,6 +24,7 @@ service Backend {
   rpc TokenizeString(PredictOptions) returns (TokenizationResponse) {}
   rpc Status(HealthMessage) returns (StatusResponse) {}
   rpc Detect(DetectOptions) returns (DetectResponse) {}
+  rpc Depth(DepthRequest) returns (DepthResponse) {}
   rpc FaceVerify(FaceVerifyRequest) returns (FaceVerifyResponse) {}
   rpc FaceAnalyze(FaceAnalyzeRequest) returns (FaceAnalyzeResponse) {}
   rpc VoiceVerify(VoiceVerifyRequest) returns (VoiceVerifyResponse) {}
@@ -670,6 +671,35 @@ message DetectResponse {
   repeated Detection Detections = 1;
 }
 
+// --- Depth estimation messages (Depth Anything 3) ---
+
+message DepthRequest {
+  string src = 1;                  // input image (filesystem path or base64-encoded payload)
+  string dst = 2;                  // optional output directory for exports (glb/colmap)
+  bool include_depth = 3;          // return the per-pixel metric depth map
+  bool include_confidence = 4;     // return the per-pixel confidence map (DualDPT)
+  bool include_pose = 5;           // return camera extrinsics/intrinsics (DualDPT)
+  bool include_sky = 6;            // return the per-pixel sky map (mono models)
+  bool include_points = 7;         // back-project to a 3D point cloud (DualDPT)
+  float points_conf_thresh = 8;    // keep points with confidence >= this threshold
+  repeated string exports = 9;     // requested exports: "glb", "colmap"
+}
+
+message DepthResponse {
+  int32 width = 1;                 // processed depth-map width
+  int32 height = 2;                // processed depth-map height
+  repeated float depth = 3;        // width*height row-major metric depth
+  repeated float confidence = 4;   // width*height row-major confidence (DualDPT)
+  repeated float sky = 5;          // width*height row-major sky map (mono)
+  repeated float extrinsics = 6;   // 12 floats, 3x4 row-major (world-to-camera)
+  repeated float intrinsics = 7;   // 9 floats, 3x3 row-major
+  int32 num_points = 8;            // number of 3D points
+  repeated float points = 9;       // num_points*3 xyz, world space
+  bytes point_colors = 10;         // num_points*3 uint8 rgb
+  repeated string export_paths = 11; // paths written for the requested exports
+  bool is_metric = 12;             // depth is in metric units
+}
+
 // --- Face recognition messages ---
 
 message FacialArea {

backend/cpp/ds4/CMakeLists.txt

@@ -9,6 +9,22 @@ option(DS4_NATIVE "Compile with -march=native / -mcpu=native" ON)
 set(DS4_GPU "cpu" CACHE STRING "GPU backend: cpu, cuda, or metal")
 set(DS4_DIR "${CMAKE_CURRENT_SOURCE_DIR}/ds4" CACHE PATH "Path to cloned ds4 source")
 
+if(${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
+    # Homebrew installs protobuf/grpc under a non-default prefix. The generated
+    # backend.pb.cc / backend.grpc.pb.cc pull in google/protobuf and grpcpp
+    # headers, but the hw_grpc_proto library links neither target, so on macOS
+    # the headers (e.g. google/protobuf/runtime_version.h) are never on the
+    # compiler's include path. Add the Homebrew prefix globally, matching the
+    # llama-cpp backend which builds on Darwin CI.
+    if(CMAKE_HOST_SYSTEM_PROCESSOR MATCHES "arm64")
+        set(HOMEBREW_DEFAULT_PREFIX "/opt/homebrew")
+    else()
+        set(HOMEBREW_DEFAULT_PREFIX "/usr/local")
+    endif()
+    link_directories("${HOMEBREW_DEFAULT_PREFIX}/lib")
+    include_directories("${HOMEBREW_DEFAULT_PREFIX}/include")
+endif()
+
 find_package(Threads REQUIRED)
 find_package(Protobuf CONFIG QUIET)
 if(NOT Protobuf_FOUND)

backend/cpp/ds4/Makefile

@@ -1,10 +1,10 @@
 # ds4 backend Makefile.
 #
-# Upstream pin lives below as DS4_VERSION?=d881f2a05e8ff6bec001315a36b794b4aa310173
+# Upstream pin lives below as DS4_VERSION?=80ebbc396aee40eedc1d829222f3362d10fa4c6c
 # (.github/bump_deps.sh) can find and update it - matches the
 # llama-cpp / ik-llama-cpp / turboquant convention.
 
-DS4_VERSION?=d881f2a05e8ff6bec001315a36b794b4aa310173
+DS4_VERSION?=80ebbc396aee40eedc1d829222f3362d10fa4c6c
 DS4_REPO?=https://github.com/antirez/ds4
 
 CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))

backend/cpp/ds4/grpc-server.cpp

@@ -25,6 +25,8 @@ extern "C" {
 #include <chrono>
 #include <climits>
 #include <csignal>
+#include <cstddef>
+#include <cstdint>
 #include <cstdlib>
 #include <cstring>
 #include <ctime>
@@ -105,6 +107,130 @@ static bool parse_layers_spec(const std::string &spec, ds4_distributed_layers *o
     return true;
 }
 
+// Parse a boolean LoadModel option. An empty value (a bare flag-style option
+// like "ssd_streaming" with no colon) means true so model YAMLs can write
+// options: ["ssd_streaming"] to enable a switch.
+static bool parse_bool_option(const std::string &s, bool *out) {
+    if (s.empty() || s == "true" || s == "1" || s == "yes" || s == "on") { *out = true; return true; }
+    if (s == "false" || s == "0" || s == "no" || s == "off") { *out = false; return true; }
+    return false;
+}
+
+// Table-driven mapping from LoadModel option keys to ds4_engine_options fields.
+// ds4_engine_options is a fixed C struct with no reflection, so the field set
+// is enumerated once here; adding a future engine knob is a one-line table
+// entry rather than a new branch in LoadModel. Two fields need ds4's own typed
+// parsers (Gib, CacheExperts) so a plain string passthrough can't cover them.
+enum class DsOptType { Bool, Int, Uint, Float, Str, Gib, CacheExperts };
+
+struct DsOptSpec {
+    const char *key;
+    DsOptType   type;
+    size_t      off;      // byte offset into ds4_engine_options
+    size_t      off2;     // second offset (CacheExperts writes experts + bytes)
+    bool        is_path;  // Str values: resolve a relative value against the model dir
+};
+
+static const DsOptSpec kEngineOptSpecs[] = {
+    {"mtp_path",                      DsOptType::Str,          offsetof(ds4_engine_options, mtp_path),                      0, true},
+    {"mtp_draft",                     DsOptType::Int,          offsetof(ds4_engine_options, mtp_draft_tokens),              0},
+    {"mtp_margin",                    DsOptType::Float,        offsetof(ds4_engine_options, mtp_margin),                    0},
+    {"prefill_chunk",                 DsOptType::Uint,         offsetof(ds4_engine_options, prefill_chunk),                 0},
+    {"power_percent",                 DsOptType::Int,          offsetof(ds4_engine_options, power_percent),                 0},
+    {"warm_weights",                  DsOptType::Bool,         offsetof(ds4_engine_options, warm_weights),                  0},
+    {"quality",                       DsOptType::Bool,         offsetof(ds4_engine_options, quality),                       0},
+    {"ssd_streaming",                 DsOptType::Bool,         offsetof(ds4_engine_options, ssd_streaming),                 0},
+    {"ssd_streaming_cold",            DsOptType::Bool,         offsetof(ds4_engine_options, ssd_streaming_cold),            0},
+    {"ssd_streaming_preload_experts", DsOptType::Uint,         offsetof(ds4_engine_options, ssd_streaming_preload_experts), 0},
+    {"ssd_streaming_cache_experts",   DsOptType::CacheExperts, offsetof(ds4_engine_options, ssd_streaming_cache_experts),
+                                                               offsetof(ds4_engine_options, ssd_streaming_cache_bytes)},
+    {"simulate_used_memory",          DsOptType::Gib,          offsetof(ds4_engine_options, simulate_used_memory_bytes),    0},
+    {"expert_profile_path",           DsOptType::Str,          offsetof(ds4_engine_options, expert_profile_path),           0, true},
+    {"directional_steering_file",     DsOptType::Str,          offsetof(ds4_engine_options, directional_steering_file),     0, true},
+    {"directional_steering_attn",     DsOptType::Float,        offsetof(ds4_engine_options, directional_steering_attn),     0},
+    {"directional_steering_ffn",      DsOptType::Float,        offsetof(ds4_engine_options, directional_steering_ffn),      0},
+};
+
+// Apply a single key:value LoadModel option to the engine options struct.
+// Unknown keys are ignored (back-compat: callers pass mixed option sets).
+// String values are copied into `storage`, whose elements the engine reads by
+// pointer during ds4_engine_open; `storage` MUST have reserved capacity so
+// push_back never reallocates and dangles an earlier c_str(). Returns false
+// with `err` set when a recognized key has an invalid value.
+static bool apply_engine_option(ds4_engine_options *opt, const std::string &key,
+                                const std::string &val, const std::string &model_dir,
+                                std::vector<std::string> &storage, std::string &err) {
+    const DsOptSpec *spec = nullptr;
+    for (const auto &s : kEngineOptSpecs) {
+        if (key == s.key) { spec = &s; break; }
+    }
+    if (!spec) return true; // unknown key: ignore
+
+    char *base = reinterpret_cast<char *>(opt);
+    switch (spec->type) {
+    case DsOptType::Bool: {
+        bool b = false;
+        if (!parse_bool_option(val, &b)) { err = key + " must be true/false"; return false; }
+        *reinterpret_cast<bool *>(base + spec->off) = b;
+        return true;
+    }
+    case DsOptType::Int: {
+        char *end = nullptr;
+        long v = std::strtol(val.c_str(), &end, 10);
+        if (val.empty() || !end || *end != '\0') { err = key + " must be an integer"; return false; }
+        *reinterpret_cast<int *>(base + spec->off) = static_cast<int>(v);
+        return true;
+    }
+    case DsOptType::Uint: {
+        char *end = nullptr;
+        long v = std::strtol(val.c_str(), &end, 10);
+        if (val.empty() || !end || *end != '\0' || v < 0 || v > static_cast<long>(UINT32_MAX)) {
+            err = key + " must be a non-negative integer"; return false;
+        }
+        *reinterpret_cast<uint32_t *>(base + spec->off) = static_cast<uint32_t>(v);
+        return true;
+    }
+    case DsOptType::Float: {
+        char *end = nullptr;
+        float f = std::strtof(val.c_str(), &end);
+        if (val.empty() || !end || *end != '\0') { err = key + " must be a number"; return false; }
+        *reinterpret_cast<float *>(base + spec->off) = f;
+        return true;
+    }
+    case DsOptType::Str: {
+        // Resolve a relative path option (e.g. mtp_path: a sibling GGUF the
+        // gallery downloaded next to the model) against the model directory, so
+        // YAMLs reference companion files by name. Absolute values pass through.
+        if (spec->is_path && !model_dir.empty() && !val.empty() && val.front() != '/') {
+            storage.push_back(model_dir + "/" + val);
+        } else {
+            storage.push_back(val);
+        }
+        *reinterpret_cast<const char **>(base + spec->off) = storage.back().c_str();
+        return true;
+    }
+    case DsOptType::Gib: {
+        uint64_t bytes = 0;
+        if (!ds4_parse_gib_arg(val.c_str(), &bytes)) {
+            err = key + " must be a GiB value, e.g. 64GB"; return false;
+        }
+        *reinterpret_cast<uint64_t *>(base + spec->off) = bytes;
+        return true;
+    }
+    case DsOptType::CacheExperts: {
+        uint32_t experts = 0;
+        uint64_t bytes = 0;
+        if (!ds4_parse_streaming_cache_experts_arg(val.c_str(), &experts, &bytes)) {
+            err = key + " must be a positive expert count or a <number>GB budget"; return false;
+        }
+        *reinterpret_cast<uint32_t *>(base + spec->off)  = experts;
+        *reinterpret_cast<uint64_t *>(base + spec->off2) = bytes;
+        return true;
+    }
+    }
+    return true;
+}
+
 // When acting as a distributed coordinator, block until the worker route
 // covers all layers (ds4_session_distributed_route_ready == 1) or the timeout
 // elapses. Returns an empty string on success, or an error message to return
@@ -476,39 +602,10 @@ public:
             return GStatus::OK;
         }
 
-        std::string mtp_path;
-        int mtp_draft = 0;
-        float mtp_margin = 3.0f;
-        std::string ds4_role, ds4_layers, ds4_listen;
-        for (const auto &opt : request->options()) {
-            auto [k, v] = split_option(opt);
-            if (k == "mtp_path") mtp_path = v;
-            else if (k == "mtp_draft") mtp_draft = std::stoi(v);
-            else if (k == "mtp_margin") mtp_margin = std::stof(v);
-            else if (k == "kv_cache_dir") g_kv_cache_dir = v;
-            else if (k == "ds4_role") ds4_role = v;
-            else if (k == "ds4_layers") ds4_layers = v;
-            else if (k == "ds4_listen") ds4_listen = v;
-            else if (k == "ds4_route_timeout") {
-                if (!parse_positive_int(v, &g_route_timeout_sec)) {
-                    result->set_success(false);
-                    result->set_message("ds4: ds4_route_timeout must be a positive integer");
-                    return GStatus::OK;
-                }
-            }
-        }
-
-        g_kv_cache.SetDir(g_kv_cache_dir);
-
         ds4_engine_options opt = {};
         opt.model_path = model_path.c_str();
-        opt.mtp_path = mtp_path.empty() ? nullptr : mtp_path.c_str();
         opt.n_threads = request->threads() > 0 ? request->threads() : 0;
-        opt.mtp_draft_tokens = mtp_draft;
-        opt.mtp_margin = mtp_margin;
-        opt.directional_steering_file = nullptr;
-        opt.warm_weights = false;
-        opt.quality = false;
+        opt.mtp_margin = 3.0f; // ds4 default; overridable via the mtp_margin option
 
 #if defined(DS4_NO_GPU)
         opt.backend = DS4_BACKEND_CPU;
@@ -518,6 +615,46 @@ public:
         opt.backend = DS4_BACKEND_CUDA;
 #endif
 
+        // Stable storage for string-valued engine options. The engine reads
+        // these by pointer during ds4_engine_open, so the std::string backing
+        // store must outlive the call and not reallocate; reserve up front so
+        // push_back keeps every prior c_str() valid. Static + clear() reuses
+        // the buffer across LoadModel calls (the old engine is closed above).
+        static std::vector<std::string> s_opt_strings;
+        s_opt_strings.clear();
+        s_opt_strings.reserve(sizeof(kEngineOptSpecs) / sizeof(kEngineOptSpecs[0]));
+
+        // Directory of the main model, used to resolve relative path options.
+        std::string model_dir;
+        if (auto slash = model_path.find_last_of('/'); slash != std::string::npos) {
+            model_dir = model_path.substr(0, slash);
+        }
+
+        std::string ds4_role, ds4_layers, ds4_listen;
+        for (const auto &o : request->options()) {
+            auto [k, v] = split_option(o);
+            if (k == "kv_cache_dir") { g_kv_cache_dir = v; continue; }
+            else if (k == "ds4_role") { ds4_role = v; continue; }
+            else if (k == "ds4_layers") { ds4_layers = v; continue; }
+            else if (k == "ds4_listen") { ds4_listen = v; continue; }
+            else if (k == "ds4_route_timeout") {
+                if (!parse_positive_int(v, &g_route_timeout_sec)) {
+                    result->set_success(false);
+                    result->set_message("ds4: ds4_route_timeout must be a positive integer");
+                    return GStatus::OK;
+                }
+                continue;
+            }
+            std::string err;
+            if (!apply_engine_option(&opt, k, v, model_dir, s_opt_strings, err)) {
+                result->set_success(false);
+                result->set_message("ds4: " + err);
+                return GStatus::OK;
+            }
+        }
+
+        g_kv_cache.SetDir(g_kv_cache_dir);
+
         // Coordinator wiring. 'ds4_role:coordinator' enables layer-split
         // distributed inference: this process listens on ds4_listen and owns
         // the ds4_layers slice; workers dial in (see `local-ai worker

backend/cpp/ik-llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-IK_LLAMA_VERSION?=e6f8112f3ba126eed3ff5b30cdd08085414a7516
+IK_LLAMA_VERSION?=71af16a6b7f6fb7315b346b4a51aad530599c3f5
 LLAMA_REPO?=https://github.com/ikawrakow/ik_llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=4c6595503fe45d5a39f88d194e270f64c7424677
+LLAMA_VERSION?=f3e182816421c648188b5eab269853bf1531d950
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/grpc-server.cpp

@@ -1922,25 +1922,27 @@ public:
                     body_json["min_p"] = data["min_p"];
                 }
 
-                // Pass enable_thinking via chat_template_kwargs (where oaicompat_chat_params_parse reads it)
+                // Forward the chat_template_kwargs the Go layer resolved (model config
+                // chat_template_kwargs + per-request metadata: enable_thinking,
+                // reasoning_effort, preserve_thinking, ...). One generic merge replaces
+                // the previous per-key handling - new template levers need no C++ change.
+                // oaicompat_chat_params_parse reads these from body_json.
                 const auto& metadata = request->metadata();
-                auto et_it = metadata.find("enable_thinking");
-                if (et_it != metadata.end()) {
-                    if (!body_json.contains("chat_template_kwargs")) {
-                        body_json["chat_template_kwargs"] = json::object();
+                auto ctk_it = metadata.find("chat_template_kwargs");
+                if (ctk_it != metadata.end() && !ctk_it->second.empty()) {
+                    try {
+                        json ctk = json::parse(ctk_it->second);
+                        if (ctk.is_object()) {
+                            if (!body_json.contains("chat_template_kwargs")) {
+                                body_json["chat_template_kwargs"] = json::object();
+                            }
+                            for (auto& el : ctk.items()) {
+                                body_json["chat_template_kwargs"][el.key()] = el.value();
+                            }
+                        }
+                    } catch (const std::exception & e) {
+                        SRV_WRN("failed to parse chat_template_kwargs metadata: %s\n", e.what());
                     }
-                    body_json["chat_template_kwargs"]["enable_thinking"] = (et_it->second == "true");
-                }
-
-                // Pass reasoning_effort via chat_template_kwargs too: the lever
-                // jinja templates like gpt-oss (Harmony) / LFM2.5 read, distinct
-                // from enable_thinking which those templates ignore.
-                auto re_it = metadata.find("reasoning_effort");
-                if (re_it != metadata.end() && !re_it->second.empty()) {
-                    if (!body_json.contains("chat_template_kwargs")) {
-                        body_json["chat_template_kwargs"] = json::object();
-                    }
-                    body_json["chat_template_kwargs"]["reasoning_effort"] = re_it->second;
                 }
 
                 // Debug: Print full body_json before template processing (includes messages, tools, tool_choice, etc.)
@@ -2756,25 +2758,26 @@ public:
                     body_json["min_p"] = data["min_p"];
                 }
 
-                // Pass enable_thinking via chat_template_kwargs (where oaicompat_chat_params_parse reads it)
+                // Forward the chat_template_kwargs the Go layer resolved (model config
+                // chat_template_kwargs + per-request metadata: enable_thinking,
+                // reasoning_effort, preserve_thinking, ...). One generic merge replaces
+                // the previous per-key handling - new template levers need no C++ change.
                 const auto& predict_metadata = request->metadata();
-                auto predict_et_it = predict_metadata.find("enable_thinking");
-                if (predict_et_it != predict_metadata.end()) {
-                    if (!body_json.contains("chat_template_kwargs")) {
-                        body_json["chat_template_kwargs"] = json::object();
+                auto predict_ctk_it = predict_metadata.find("chat_template_kwargs");
+                if (predict_ctk_it != predict_metadata.end() && !predict_ctk_it->second.empty()) {
+                    try {
+                        json ctk = json::parse(predict_ctk_it->second);
+                        if (ctk.is_object()) {
+                            if (!body_json.contains("chat_template_kwargs")) {
+                                body_json["chat_template_kwargs"] = json::object();
+                            }
+                            for (auto& el : ctk.items()) {
+                                body_json["chat_template_kwargs"][el.key()] = el.value();
+                            }
+                        }
+                    } catch (const std::exception & e) {
+                        SRV_WRN("failed to parse chat_template_kwargs metadata: %s\n", e.what());
                     }
-                    body_json["chat_template_kwargs"]["enable_thinking"] = (predict_et_it->second == "true");
-                }
-
-                // Pass reasoning_effort via chat_template_kwargs too: the lever
-                // jinja templates like gpt-oss (Harmony) / LFM2.5 read, distinct
-                // from enable_thinking which those templates ignore.
-                auto predict_re_it = predict_metadata.find("reasoning_effort");
-                if (predict_re_it != predict_metadata.end() && !predict_re_it->second.empty()) {
-                    if (!body_json.contains("chat_template_kwargs")) {
-                        body_json["chat_template_kwargs"] = json::object();
-                    }
-                    body_json["chat_template_kwargs"]["reasoning_effort"] = predict_re_it->second;
                 }
 
                 // Debug: Print full body_json before template processing (includes messages, tools, tool_choice, etc.)

backend/cpp/privacy-filter/.gitignore

@@ -0,0 +1,9 @@
+/privacy-filter.cpp
+build/
+package/
+grpc-server
+*.o
+backend.pb.cc
+backend.pb.h
+backend.grpc.pb.cc
+backend.grpc.pb.h

backend/cpp/privacy-filter/CMakeLists.txt

@@ -0,0 +1,69 @@
+cmake_minimum_required(VERSION 3.21)
+project(privacy-filter-grpc-server LANGUAGES CXX C)
+
+set(CMAKE_CXX_STANDARD 17)
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+set(TARGET grpc-server)
+
+# Path to the privacy-filter.cpp engine sources. The Makefile arranges for this
+# to exist (clone of a pinned commit, or a symlink to PRIVACY_FILTER_SRC).
+set(PRIVACY_FILTER_DIR "${CMAKE_CURRENT_SOURCE_DIR}/privacy-filter.cpp"
+    CACHE PATH "Path to the privacy-filter.cpp engine source tree")
+
+find_package(Threads REQUIRED)
+find_package(Protobuf CONFIG QUIET)
+if(NOT Protobuf_FOUND)
+    find_package(Protobuf REQUIRED)
+endif()
+find_package(gRPC CONFIG QUIET)
+if(NOT gRPC_FOUND)
+    # Ubuntu's apt-installed grpc++ does not ship a CMake config - fall back.
+    find_library(GRPCPP_LIB grpc++ REQUIRED)
+    find_library(GRPCPP_REFLECTION_LIB grpc++_reflection REQUIRED)
+    add_library(gRPC::grpc++ INTERFACE IMPORTED)
+    set_target_properties(gRPC::grpc++ PROPERTIES INTERFACE_LINK_LIBRARIES "${GRPCPP_LIB}")
+    add_library(gRPC::grpc++_reflection INTERFACE IMPORTED)
+    set_target_properties(gRPC::grpc++_reflection PROPERTIES INTERFACE_LINK_LIBRARIES "${GRPCPP_REFLECTION_LIB}")
+endif()
+
+find_program(_PROTOC NAMES protoc REQUIRED)
+find_program(_GRPC_CPP_PLUGIN NAMES grpc_cpp_plugin REQUIRED)
+
+get_filename_component(HW_PROTO "${CMAKE_CURRENT_SOURCE_DIR}/../../backend.proto" ABSOLUTE)
+get_filename_component(HW_PROTO_PATH "${HW_PROTO}" PATH)
+
+set(HW_PROTO_SRCS "${CMAKE_CURRENT_BINARY_DIR}/backend.pb.cc")
+set(HW_PROTO_HDRS "${CMAKE_CURRENT_BINARY_DIR}/backend.pb.h")
+set(HW_GRPC_SRCS  "${CMAKE_CURRENT_BINARY_DIR}/backend.grpc.pb.cc")
+set(HW_GRPC_HDRS  "${CMAKE_CURRENT_BINARY_DIR}/backend.grpc.pb.h")
+
+add_custom_command(
+    OUTPUT "${HW_PROTO_SRCS}" "${HW_PROTO_HDRS}" "${HW_GRPC_SRCS}" "${HW_GRPC_HDRS}"
+    COMMAND ${_PROTOC}
+    ARGS --grpc_out "${CMAKE_CURRENT_BINARY_DIR}"
+         --cpp_out  "${CMAKE_CURRENT_BINARY_DIR}"
+         -I "${HW_PROTO_PATH}"
+         --plugin=protoc-gen-grpc="${_GRPC_CPP_PLUGIN}"
+         "${HW_PROTO}"
+    DEPENDS "${HW_PROTO}")
+
+add_library(hw_grpc_proto STATIC
+    ${HW_GRPC_SRCS} ${HW_GRPC_HDRS}
+    ${HW_PROTO_SRCS} ${HW_PROTO_HDRS})
+target_include_directories(hw_grpc_proto PUBLIC ${CMAKE_CURRENT_BINARY_DIR})
+
+# Build only the pf static lib (+ ggml) from the engine tree — no CLI/bench/tests.
+# PF_VULKAN is honored when passed on the cmake command line (it lands in the
+# shared cache the engine reads).
+set(PF_BUILD_TOOLS OFF CACHE BOOL "" FORCE)
+set(PF_BUILD_TESTS OFF CACHE BOOL "" FORCE)
+add_subdirectory(${PRIVACY_FILTER_DIR} ${CMAKE_CURRENT_BINARY_DIR}/privacy-filter.cpp)
+
+add_executable(${TARGET} grpc-server.cpp)
+target_link_libraries(${TARGET} PRIVATE
+    pf
+    hw_grpc_proto
+    gRPC::grpc++
+    gRPC::grpc++_reflection
+    protobuf::libprotobuf
+    Threads::Threads)

backend/cpp/privacy-filter/Makefile

@@ -0,0 +1,77 @@
+# privacy-filter backend Makefile.
+#
+# Wraps the standalone privacy-filter.cpp GGML engine (the openai-privacy-filter
+# PII/NER token classifier) as a LocalAI gRPC backend. The engine source is
+# fetched at the pin below — .github/workflows/bump_deps.yaml finds and updates
+# PRIVACY_FILTER_VERSION, matching the llama-cpp / ds4 convention.
+#
+# Local development: point at a working checkout instead of cloning, e.g.
+#   make PRIVACY_FILTER_SRC=$HOME/c/privacy-filter.cpp grpc-server
+
+PRIVACY_FILTER_VERSION?=646342f7a59c6b7d195185eac60bad762e572f1d
+PRIVACY_FILTER_REPO?=https://github.com/localai-org/privacy-filter.cpp
+PRIVACY_FILTER_SRC?=
+
+CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
+BUILD_DIR := build
+
+BUILD_TYPE ?=
+NATIVE ?= false
+JOBS ?= $(shell nproc 2>/dev/null || echo 4)
+
+CMAKE_ARGS ?= -DCMAKE_BUILD_TYPE=Release
+
+# GPU backends; the default (cpu) needs no extra flags. 'cublas' is LocalAI's
+# name for the CUDA build (matches llama-cpp / ds4), mapping to the engine's
+# GGML_CUDA path; 'vulkan' selects the ggml Vulkan backend.
+ifeq ($(BUILD_TYPE),cublas)
+    CMAKE_ARGS += -DPF_CUDA=ON
+endif
+ifeq ($(BUILD_TYPE),vulkan)
+    CMAKE_ARGS += -DPF_VULKAN=ON
+endif
+
+# Portable binaries for distribution: disable -march=native unless asked.
+ifneq ($(NATIVE),true)
+    CMAKE_ARGS += -DGGML_NATIVE=OFF
+endif
+
+.PHONY: grpc-server package clean purge test all
+all: grpc-server
+
+# Provide the engine sources at ./privacy-filter.cpp. With PRIVACY_FILTER_SRC
+# set we symlink a local checkout (instant, no network); otherwise we clone the
+# pinned commit and its ggml submodule. The directory/symlink is the target, so
+# make only does this once — run 'make purge && make' to refetch after a bump.
+privacy-filter.cpp:
+ifneq ($(PRIVACY_FILTER_SRC),)
+	ln -sfn $(abspath $(PRIVACY_FILTER_SRC)) privacy-filter.cpp
+else
+	mkdir -p privacy-filter.cpp
+	cd privacy-filter.cpp && \
+	git init -q && \
+	git remote add origin $(PRIVACY_FILTER_REPO) && \
+	git fetch --depth 1 origin $(PRIVACY_FILTER_VERSION) && \
+	git checkout FETCH_HEAD && \
+	git submodule update --init --recursive --depth 1
+endif
+
+grpc-server: privacy-filter.cpp
+	@echo "Building privacy-filter grpc-server ($(BUILD_TYPE)) with $(CMAKE_ARGS)"
+	mkdir -p $(BUILD_DIR)
+	cd $(BUILD_DIR) && cmake $(CMAKE_ARGS) $(CURRENT_MAKEFILE_DIR) && cmake --build . --config Release -j $(JOBS)
+	cp $(BUILD_DIR)/grpc-server grpc-server
+
+package: grpc-server
+	bash package.sh
+
+test:
+	@echo "privacy-filter backend: parity/regression coverage lives in the engine repo"
+
+clean:
+	rm -rf $(BUILD_DIR) grpc-server package
+
+# 'privacy-filter.cpp' may be a symlink (PRIVACY_FILTER_SRC) — rm without a
+# trailing slash removes the link, never the linked-to checkout.
+purge: clean
+	rm -rf privacy-filter.cpp

backend/cpp/privacy-filter/grpc-server.cpp

@@ -0,0 +1,210 @@
+// privacy-filter LocalAI gRPC backend.
+//
+// Thin shim over privacy-filter.cpp's flat C API (include/pf.h): a standalone
+// GGML engine for the openai-privacy-filter token-classification model family
+// (PII NER). It replaces the llama.cpp-patched TokenClassify path for this one
+// model family — same GGUF files, no llama.cpp carry-patches.
+//
+// Only the RPCs the PII tier needs are implemented: LoadModel, TokenClassify,
+// plus Health / Status / Free. Everything else inherits the generated base
+// class default (UNIMPLEMENTED).
+
+#include "backend.pb.h"
+#include "backend.grpc.pb.h"
+
+#include "pf.h"
+
+#include <grpcpp/grpcpp.h>
+#include <grpcpp/server.h>
+#include <grpcpp/server_builder.h>
+#include <grpcpp/ext/proto_server_reflection_plugin.h>
+
+#include <atomic>
+#include <chrono>
+#include <csignal>
+#include <iostream>
+#include <memory>
+#include <mutex>
+#include <string>
+
+using grpc::Server;
+using grpc::ServerBuilder;
+using grpc::ServerContext;
+// NOTE: do NOT alias grpc::Status as Status — the Status RPC method below would
+// shadow the type and break the other method signatures. Use GStatus instead.
+using GStatus = ::grpc::Status;
+using grpc::StatusCode;
+
+namespace {
+
+// The engine is single-model-per-process: LocalAI spawns one backend process
+// per loaded model. g_mu guards (re)load against in-flight classification.
+std::mutex          g_mu;
+pf_ctx *            g_ctx = nullptr;
+std::atomic<Server *> g_server{nullptr};
+
+// Resolve the device string the engine expects ("cpu" / "gpu" / "cuda" /
+// "vulkan", optionally ":N"). Priority: an explicit "device:..." in
+// ModelOptions.Options, then a non-zero NGPULayers as a coarse "use the GPU"
+// signal, else CPU. "gpu" lets the engine pick whichever GPU backend this
+// binary was compiled with (CUDA or Vulkan), so the same config works on
+// either build; pin "device:cuda"/"device:vulkan" to be explicit.
+std::string resolve_device(const backend::ModelOptions * opts) {
+    for (const auto & o : opts->options()) {
+        const std::string prefix = "device:";
+        if (o.rfind(prefix, 0) == 0) {
+            return o.substr(prefix.size());
+        }
+    }
+    if (opts->ngpulayers() > 0) {
+        return "gpu";
+    }
+    return "cpu";
+}
+
+class PrivacyFilterBackend final : public backend::Backend::Service {
+public:
+    GStatus Health(ServerContext *, const backend::HealthMessage *,
+                   backend::Reply * reply) override {
+        reply->set_message("OK");
+        return GStatus::OK;
+    }
+
+    GStatus Status(ServerContext *, const backend::HealthMessage *,
+                   backend::StatusResponse * response) override {
+        std::lock_guard<std::mutex> lock(g_mu);
+        response->set_state(g_ctx ? backend::StatusResponse::READY
+                                  : backend::StatusResponse::UNINITIALIZED);
+        return GStatus::OK;
+    }
+
+    GStatus LoadModel(ServerContext *, const backend::ModelOptions * request,
+                      backend::Result * result) override {
+        std::lock_guard<std::mutex> lock(g_mu);
+
+        // ModelFile is the absolute path LocalAI resolves; Model is the bare
+        // name. Prefer the former, fall back to the latter.
+        const std::string path =
+            !request->modelfile().empty() ? request->modelfile() : request->model();
+        if (path.empty()) {
+            result->set_success(false);
+            result->set_message("no model path supplied");
+            return GStatus::OK;
+        }
+
+        const std::string device = resolve_device(request);
+
+        if (g_ctx) { pf_free(g_ctx); g_ctx = nullptr; }
+
+        pf_ctx * ctx = pf_load(path.c_str(), device.c_str(), request->threads());
+        const char * err = pf_last_error(ctx);
+        if (err) {
+            result->set_success(false);
+            result->set_message(std::string("privacy-filter load failed: ") + err);
+            pf_free(ctx);
+            return GStatus::OK;
+        }
+
+        // ContextSize, when set, becomes the per-forward window. The engine
+        // ignores values that are too small to window (<= 2*halo) and just
+        // runs a single forward, so passing it through is always safe.
+        if (request->contextsize() > 0) {
+            pf_set_window(ctx, request->contextsize());
+        }
+
+        g_ctx = ctx;
+        result->set_success(true);
+        result->set_message("privacy-filter loaded (" + device + ")");
+        return GStatus::OK;
+    }
+
+    GStatus TokenClassify(ServerContext *, const backend::TokenClassifyRequest * request,
+                          backend::TokenClassifyResponse * response) override {
+        std::lock_guard<std::mutex> lock(g_mu);
+        if (!g_ctx) {
+            return GStatus(StatusCode::FAILED_PRECONDITION, "Model not loaded");
+        }
+
+        const std::string & text = request->text();
+        if (text.empty()) {
+            return GStatus::OK;  // no text -> no entities
+        }
+
+        pf_entity * ents = nullptr;
+        size_t      n    = 0;
+        if (pf_classify(g_ctx, text.data(), text.size(), request->threshold(), &ents, &n) != 0) {
+            const char * err = pf_last_error(g_ctx);
+            return GStatus(StatusCode::INTERNAL,
+                           std::string("TokenClassify failed: ") + (err ? err : "unknown"));
+        }
+
+        // Byte offsets are into the original UTF-8 text; the engine already
+        // applied the threshold and whitespace-trimmed span edges.
+        for (size_t i = 0; i < n; i++) {
+            backend::TokenClassifyEntity * ent = response->add_entities();
+            ent->set_entity_group(ents[i].label ? ents[i].label : "");
+            ent->set_start(ents[i].start);
+            ent->set_end(ents[i].end);
+            ent->set_score(ents[i].score);
+            ent->set_text(text.substr((size_t) ents[i].start,
+                                      (size_t) (ents[i].end - ents[i].start)));
+        }
+        pf_entities_free(ents, n);
+        return GStatus::OK;
+    }
+
+    GStatus Free(ServerContext *, const backend::HealthMessage *,
+                 backend::Result * result) override {
+        std::lock_guard<std::mutex> lock(g_mu);
+        if (g_ctx) { pf_free(g_ctx); g_ctx = nullptr; }
+        result->set_success(true);
+        return GStatus::OK;
+    }
+};
+
+void RunServer(const std::string & addr) {
+    PrivacyFilterBackend service;
+    grpc::EnableDefaultHealthCheckService(true);
+    grpc::reflection::InitProtoReflectionServerBuilderPlugin();
+
+    ServerBuilder builder;
+    builder.AddListeningPort(addr, grpc::InsecureServerCredentials());
+    builder.RegisterService(&service);
+    builder.SetMaxReceiveMessageSize(64 * 1024 * 1024);
+    builder.SetMaxSendMessageSize(64 * 1024 * 1024);
+
+    std::unique_ptr<Server> server(builder.BuildAndStart());
+    if (!server) {
+        std::cerr << "privacy-filter grpc-server: failed to bind " << addr << "\n";
+        std::exit(1);
+    }
+    g_server = server.get();
+    std::cerr << "privacy-filter grpc-server listening on " << addr << "\n";
+    server->Wait();
+}
+
+void signal_handler(int) {
+    if (auto * srv = g_server.load()) {
+        srv->Shutdown(std::chrono::system_clock::now() + std::chrono::seconds(3));
+    }
+}
+
+} // namespace
+
+int main(int argc, char * argv[]) {
+    std::string addr = "127.0.0.1:50051";
+    for (int i = 1; i < argc; ++i) {
+        std::string a = argv[i];
+        const std::string addr_flag = "--addr=";
+        if (a.rfind(addr_flag, 0) == 0)      addr = a.substr(addr_flag.size());
+        else if (a == "--addr" && i + 1 < argc) addr = argv[++i];
+        else if (a == "--help" || a == "-h") {
+            std::cout << "Usage: grpc-server --addr=HOST:PORT\n";
+            return 0;
+        }
+    }
+    std::signal(SIGINT,  signal_handler);
+    std::signal(SIGTERM, signal_handler);
+    RunServer(addr);
+    return 0;
+}

backend/cpp/privacy-filter/package.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+# Assemble package/ for the from-scratch backend image: the grpc-server binary,
+# run.sh, the dynamic loader, and every shared library the binary needs.
+set -e
+CURDIR=$(dirname "$(realpath "$0")")
+REPO_ROOT="${CURDIR}/../../.."
+
+mkdir -p "$CURDIR/package/lib"
+cp -avf "$CURDIR/grpc-server" "$CURDIR/package/"
+cp -rfv "$CURDIR/run.sh"      "$CURDIR/package/"
+
+# The dynamic loader, renamed to lib/ld.so so run.sh can invoke it explicitly
+# (makes the image independent of the host's glibc layout).
+if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
+    cp -arfLv /lib64/ld-linux-x86-64.so.2 "$CURDIR/package/lib/ld.so"
+elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
+    cp -arfLv /lib/ld-linux-aarch64.so.1 "$CURDIR/package/lib/ld.so"
+else
+    echo "package.sh: unknown architecture" >&2; exit 1
+fi
+
+# Bundle the binary's transitive shared deps (libstdc++, libgomp, and the apt
+# grpc++/protobuf/absl stack) by walking ldd — robust to whichever of those are
+# linked shared vs static. The loader line (no "=>") is skipped; ld.so above
+# already covers it.
+ldd "$CURDIR/grpc-server" | awk '$2 == "=>" && $3 ~ /^\// { print $3 }' | sort -u | \
+while read -r so; do
+    [ -f "$so" ] && cp -arfLv "$so" "$CURDIR/package/lib/"
+done
+
+# Vulkan loader / GPU libs when building the GPU variant.
+GPU_LIB_SCRIPT="${REPO_ROOT}/scripts/build/package-gpu-libs.sh"
+if [ -f "$GPU_LIB_SCRIPT" ]; then
+    source "$GPU_LIB_SCRIPT" "$CURDIR/package/lib"
+    package_gpu_libs
+fi
+
+echo "privacy-filter package contents:"
+ls -lah "$CURDIR/package/" "$CURDIR/package/lib/"

backend/cpp/privacy-filter/run.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+# Entry point for the privacy-filter backend image / BACKEND_BINARY mode.
+set -e
+CURDIR=$(dirname "$(realpath "$0")")
+export LD_LIBRARY_PATH="$CURDIR/lib:$LD_LIBRARY_PATH"
+if [ -f "$CURDIR/lib/ld.so" ]; then
+    exec "$CURDIR/lib/ld.so" "$CURDIR/grpc-server" "$@"
+fi
+exec "$CURDIR/grpc-server" "$@"

backend/go/depth-anything-cpp/.gitignore

@@ -0,0 +1,7 @@
+sources/
+build*/
+package/
+libdepthanythingcpp*.so
+depth-anything-cpp
+test-models/
+test-data/

backend/go/depth-anything-cpp/CMakeLists.txt

@@ -0,0 +1,28 @@
+cmake_minimum_required(VERSION 3.18)
+project(libdepthanythingcpp LANGUAGES C CXX)
+
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+set(CMAKE_CXX_STANDARD 17)
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+
+# Static-link ggml into the depth-anything shared library so the resulting .so
+# has no runtime dependency on an external libggml — only on
+# libc/libstdc++/libgomp, which the LocalAI package step bundles into the
+# docker image.
+set(BUILD_SHARED_LIBS OFF CACHE BOOL "Build static libraries" FORCE)
+
+# depth-anything.cpp build switches: skip CLI/tests, but build libdepthanything
+# itself as a SHARED library (DA_SHARED) while ggml stays static
+# (BUILD_SHARED_LIBS OFF above). The da_capi_* C ABI is compiled into
+# src/da_capi.cpp and re-exported by that shared library, so no extra MODULE
+# wrapper is needed (unlike locate-anything.cpp).
+set(DA_BUILD_CLI OFF CACHE BOOL "Disable depth-anything CLI" FORCE)
+set(DA_BUILD_TESTS OFF CACHE BOOL "Disable depth-anything tests" FORCE)
+set(DA_SHARED ON CACHE BOOL "Build libdepthanything as a shared lib" FORCE)
+
+add_subdirectory(./sources/depth-anything.cpp)
+
+# Emit libdepthanything.so into the top-level build dir so the Makefile can
+# rename it to the per-variant libdepthanythingcpp-<variant>.so.
+set_target_properties(depthanything PROPERTIES
+    LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})

backend/go/depth-anything-cpp/Makefile

@@ -0,0 +1,139 @@
+CMAKE_ARGS?=
+BUILD_TYPE?=
+NATIVE?=false
+
+GOCMD?=go
+GO_TAGS?=
+JOBS?=$(shell nproc --ignore=1)
+
+# depth-anything.cpp. Pin to a specific commit for a stable build; a squash
+# merge upstream can orphan a branch, so the native version is pinned by SHA.
+# This SHA adds the nested two-file metric C-API (abi_version 4,
+# da_capi_load_nested) required by the depth-anything-3-nested gallery model;
+# tag it (e.g. v0.1.3) upstream to keep the SHA alive.
+DEPTHANYTHING_REPO?=https://github.com/mudler/depth-anything.cpp.git
+DEPTHANYTHING_VERSION?=cce5edc395fd1843806093d7ccc0c8b0d0b97b72
+
+ifeq ($(NATIVE),false)
+	CMAKE_ARGS+=-DGGML_NATIVE=OFF
+endif
+
+# Forward LocalAI's BUILD_TYPE to the matching ggml backend switch. depth-anything.cpp
+# force-sets GGML_CUDA/GGML_VULKAN/GGML_METAL from its own DA_GGML_* options, so
+# those must be toggled via the DA_GGML_* names (a bare -DGGML_CUDA=ON would be
+# overridden); the remaining ggml switches pass straight through.
+ifeq ($(BUILD_TYPE),cublas)
+	CMAKE_ARGS+=-DGGML_CUDA=ON -DDA_GGML_CUDA=ON
+else ifeq ($(BUILD_TYPE),openblas)
+	CMAKE_ARGS+=-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
+else ifeq ($(BUILD_TYPE),clblas)
+	CMAKE_ARGS+=-DGGML_CLBLAST=ON
+else ifeq ($(BUILD_TYPE),hipblas)
+	ROCM_HOME ?= /opt/rocm
+	ROCM_PATH ?= /opt/rocm
+	export CXX=$(ROCM_HOME)/llvm/bin/clang++
+	export CC=$(ROCM_HOME)/llvm/bin/clang
+	AMDGPU_TARGETS?=gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1200,gfx1201
+	CMAKE_ARGS+=-DGGML_HIPBLAS=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
+else ifeq ($(BUILD_TYPE),vulkan)
+	CMAKE_ARGS+=-DGGML_VULKAN=ON -DDA_GGML_VULKAN=ON
+else ifeq ($(OS),Darwin)
+	ifneq ($(BUILD_TYPE),metal)
+		CMAKE_ARGS+=-DGGML_METAL=OFF
+	else
+		CMAKE_ARGS+=-DGGML_METAL=ON
+		CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=ON
+		CMAKE_ARGS+=-DDA_GGML_METAL=ON
+	endif
+endif
+
+ifeq ($(BUILD_TYPE),sycl_f16)
+	CMAKE_ARGS+=-DGGML_SYCL=ON \
+		-DCMAKE_C_COMPILER=icx \
+		-DCMAKE_CXX_COMPILER=icpx \
+		-DGGML_SYCL_F16=ON
+endif
+
+ifeq ($(BUILD_TYPE),sycl_f32)
+	CMAKE_ARGS+=-DGGML_SYCL=ON \
+		-DCMAKE_C_COMPILER=icx \
+		-DCMAKE_CXX_COMPILER=icpx
+endif
+
+sources/depth-anything.cpp:
+	mkdir -p sources && \
+	git clone --recursive $(DEPTHANYTHING_REPO) sources/depth-anything.cpp && \
+	cd sources/depth-anything.cpp && \
+	git checkout $(DEPTHANYTHING_VERSION) && \
+	git submodule update --init --recursive --depth 1 --single-branch
+
+# Detect OS
+UNAME_S := $(shell uname -s)
+
+# Only build CPU variants on Linux
+ifeq ($(UNAME_S),Linux)
+	VARIANT_TARGETS = libdepthanythingcpp-avx.so libdepthanythingcpp-avx2.so libdepthanythingcpp-avx512.so libdepthanythingcpp-fallback.so
+else
+	# On non-Linux (e.g., Darwin), build only fallback variant
+	VARIANT_TARGETS = libdepthanythingcpp-fallback.so
+endif
+
+depth-anything-cpp: main.go godepthanythingcpp.go $(VARIANT_TARGETS)
+	CGO_ENABLED=0 $(GOCMD) build -tags "$(GO_TAGS)" -o depth-anything-cpp ./
+
+package: depth-anything-cpp
+	bash package.sh
+
+build: package
+
+clean: purge
+	rm -rf libdepthanythingcpp*.so depth-anything-cpp package sources
+
+purge:
+	rm -rf build*
+
+# Build all variants (Linux only)
+ifeq ($(UNAME_S),Linux)
+libdepthanythingcpp-avx.so: sources/depth-anything.cpp
+	rm -rfv build-$@
+	$(info ${GREEN}I depth-anything-cpp build info:avx${RESET})
+	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libdepthanythingcpp-custom
+	rm -rfv build-$@
+
+libdepthanythingcpp-avx2.so: sources/depth-anything.cpp
+	rm -rfv build-$@
+	$(info ${GREEN}I depth-anything-cpp build info:avx2${RESET})
+	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) libdepthanythingcpp-custom
+	rm -rfv build-$@
+
+libdepthanythingcpp-avx512.so: sources/depth-anything.cpp
+	rm -rfv build-$@
+	$(info ${GREEN}I depth-anything-cpp build info:avx512${RESET})
+	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=on -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) libdepthanythingcpp-custom
+	rm -rfv build-$@
+endif
+
+# Build fallback variant (all platforms)
+libdepthanythingcpp-fallback.so: sources/depth-anything.cpp
+	rm -rfv build-$@
+	$(info ${GREEN}I depth-anything-cpp build info:fallback${RESET})
+	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libdepthanythingcpp-custom
+	rm -rfv build-$@
+
+libdepthanythingcpp-custom: CMakeLists.txt
+	mkdir -p build-$(SO_TARGET) && \
+	cd build-$(SO_TARGET) && \
+	cmake .. $(CMAKE_ARGS) && \
+	cmake --build . --config Release -j$(JOBS) && \
+	cd .. && \
+	mv build-$(SO_TARGET)/libdepthanything.so ./$(SO_TARGET)
+
+all: depth-anything-cpp package
+
+# `test` is invoked by the top-level Makefile's `test-extra` target. It builds
+# the backend binary + the fallback shared library (needed for dlopen at
+# runtime), then runs test.sh which downloads a small GGUF + a test image and
+# exercises the gRPC Load/Predict wire path via the Go smoke test in
+# main_test.go.
+test: depth-anything-cpp libdepthanythingcpp-fallback.so
+	bash test.sh

backend/go/depth-anything-cpp/godepthanythingcpp.go

@@ -0,0 +1,556 @@
+package main
+
+// godepthanythingcpp.go - gRPC handlers (Load, Predict, GenerateImage) for the
+// depth-anything-cpp backend, wrapping the Depth Anything 3 ggml C-API
+// (libdepthanythingcpp-<variant>.so) via purego.
+//
+// Embeds base.SingleThread to default the unimplemented RPCs to "not supported"
+// and to serialize calls — the C side shares a ggml graph allocator and is NOT
+// reentrant, so all inference must run one-at-a-time.
+//
+// Depth has no native OpenAI endpoint, so the model is exposed two ways:
+//
+//   - GenerateImage(src, dst): run depth on the src image and write a
+//     min-max-normalised grayscale depth PNG to dst.
+//   - Predict(images[0]): run depth+pose and return a JSON blob with the depth
+//     dimensions, depth stats and the camera extrinsics (3x4) / intrinsics (3x3).
+
+import (
+	"encoding/base64"
+	"encoding/json"
+	"fmt"
+	"image"
+	"image/png"
+	"math"
+	"os"
+	"path/filepath"
+	"strings"
+	"unsafe"
+
+	"github.com/mudler/LocalAI/pkg/grpc/base"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+)
+
+// C-API function pointers, registered in main.go via purego. The da_capi_*
+// symbols live inside libdepthanything (src/da_capi.cpp) and are re-exported by
+// the DA_SHARED build.
+var (
+	// da_capi_load(const char* gguf_path, int n_threads) -> da_ctx* (0 = fail)
+	CapiLoad func(gguf string, nThreads int32) uintptr
+	// da_capi_load_nested(const char* anyview_gguf, const char* metric_gguf,
+	//   int n_threads) -> da_ctx* (0 = fail). The returned ctx serves the nested
+	//   metric model: depth/pose calls produce final metric-scale depth + scaled pose.
+	CapiLoadNested func(anyview string, metric string, nThreads int32) uintptr
+	// da_capi_free(da_ctx* ctx) — safe on a 0 handle.
+	CapiFree func(handle uintptr)
+	// da_capi_last_error(da_ctx* ctx) -> const char* (owned by ctx, "" if none).
+	// purego marshals the returned C string into a Go string (a copy), so we
+	// never free it.
+	CapiLastError func(handle uintptr) string
+	// da_capi_depth_path(ctx, image_path, out_h*, out_w*) -> float* depth map
+	// (row-major H*W); nil on error. Caller frees via da_capi_free_floats.
+	CapiDepthPath func(handle uintptr, imagePath string, outH *int32, outW *int32) *float32
+	// da_capi_free_floats(float* p)
+	CapiFreeFloats func(p *float32)
+	// da_capi_pose_path(ctx, image_path, out_ext[12], out_intr[9]) -> 0 ok, -1 err
+	CapiPosePath func(handle uintptr, imagePath string, outExt *float32, outIntr *float32) int32
+	// da_capi_depth_dense(ctx, image_path, out_h*, out_w*, out_depth**, out_conf**,
+	//   out_sky**, out_ext[12], out_intr[9], out_is_metric*) -> 0 ok, -1 err.
+	// Each non-NULL out_depth/out_conf/out_sky receives a malloc'd float[H*W] (free
+	// via da_capi_free_floats); buffers the model doesn't produce are set NULL.
+	CapiDepthDense func(handle uintptr, imagePath string,
+		outH, outW *int32,
+		outDepth, outConf, outSky **float32,
+		outExt, outIntr *float32,
+		outIsMetric *int32) int32
+	// da_capi_points(ctx, image_path, conf_thresh, out_n*, out_xyz**, out_rgb**) ->
+	//   0 ok, -1 err. *out_xyz = malloc'd float[3*N] (free via da_capi_free_floats),
+	//   *out_rgb = malloc'd uint8[3*N] (free via da_capi_free_bytes).
+	CapiPoints func(handle uintptr, imagePath string, confThresh float32,
+		outN *int32, outXyz **float32, outRgb **byte) int32
+	// da_capi_free_bytes(unsigned char* p)
+	CapiFreeBytes func(p *byte)
+	// da_capi_export_glb(ctx, image_path, out_glb) -> 0 ok, -1 err
+	CapiExportGlb func(handle uintptr, imagePath string, outGlb string) int32
+	// da_capi_export_colmap(ctx, image_path, out_dir, binary) -> 0 ok, -1 err
+	CapiExportColmap func(handle uintptr, imagePath string, outDir string, binary int32) int32
+)
+
+type DepthAnythingCpp struct {
+	base.SingleThread
+	handle uintptr
+}
+
+// Load loads the GGUF model at opts.ModelFile (joined with opts.ModelPath if
+// relative) and stores the da_ctx handle for later inference calls.
+func (r *DepthAnythingCpp) Load(opts *pb.ModelOptions) error {
+	modelFile := opts.ModelFile
+	if modelFile == "" {
+		modelFile = opts.Model
+	}
+	if modelFile == "" {
+		return fmt.Errorf("depth-anything-cpp: ModelFile is empty")
+	}
+
+	resolve := func(name string) string {
+		if filepath.IsAbs(name) {
+			return name
+		}
+		return filepath.Join(opts.ModelPath, name)
+	}
+	modelPath := resolve(modelFile)
+
+	if _, err := os.Stat(modelPath); err != nil {
+		return fmt.Errorf("depth-anything-cpp: model file not found: %s: %w", modelPath, err)
+	}
+
+	// Nested metric models are a two-file pair: the main model is the anyview
+	// (GIANT) branch and the metric (ViT-L + DPT/sky) branch is named via a
+	// "metric_model:<filename>" entry in opts.Options. When present we load both
+	// branches so the engine runs the nested metric alignment.
+	metricFile := optionValue(opts.Options, "metric_model")
+
+	threads := opts.Threads
+	if threads <= 0 {
+		threads = 4
+	}
+
+	// Release previous model if any (re-Load).
+	if r.handle != 0 {
+		CapiFree(r.handle)
+		r.handle = 0
+	}
+
+	var h uintptr
+	if metricFile != "" {
+		metricPath := resolve(metricFile)
+		if _, err := os.Stat(metricPath); err != nil {
+			return fmt.Errorf("depth-anything-cpp: metric_model file not found: %s: %w", metricPath, err)
+		}
+		h = CapiLoadNested(modelPath, metricPath, threads)
+		if h == 0 {
+			if msg := CapiLastError(0); msg != "" {
+				return fmt.Errorf("depth-anything-cpp: da_capi_load_nested failed for %s + %s: %s", modelPath, metricPath, msg)
+			}
+			return fmt.Errorf("depth-anything-cpp: da_capi_load_nested failed for %s + %s", modelPath, metricPath)
+		}
+	} else {
+		h = CapiLoad(modelPath, threads)
+		if h == 0 {
+			// da_capi_last_error needs a ctx; on a failed load we have none (it
+			// returns "" for a null ctx), so the text is best-effort.
+			if msg := CapiLastError(0); msg != "" {
+				return fmt.Errorf("depth-anything-cpp: da_capi_load failed for %s: %s", modelPath, msg)
+			}
+			return fmt.Errorf("depth-anything-cpp: da_capi_load failed for %s", modelPath)
+		}
+	}
+	r.handle = h
+	return nil
+}
+
+// optionValue returns the value of the first "key:value" entry in opts whose key
+// matches (case-sensitive), or "" if absent. Mirrors how other LocalAI backends
+// read ModelOptions.Options.
+func optionValue(opts []string, key string) string {
+	prefix := key + ":"
+	for _, o := range opts {
+		if strings.HasPrefix(o, prefix) {
+			return strings.TrimSpace(o[len(prefix):])
+		}
+	}
+	return ""
+}
+
+// depthResult is the JSON payload returned by Predict.
+type depthResult struct {
+	DepthW     int         `json:"depth_w"`
+	DepthH     int         `json:"depth_h"`
+	DepthMin   float32     `json:"depth_min"`
+	DepthMax   float32     `json:"depth_max"`
+	Extrinsics [12]float32 `json:"extrinsics"` // 3x4 row-major
+	Intrinsics [9]float32  `json:"intrinsics"` // 3x3 row-major
+}
+
+// Predict runs depth+pose on the first supplied image and returns depth
+// statistics + camera pose as a JSON string. LocalAI wraps the string into the
+// Reply.Message of the gRPC response. The image in Images[0] may be a
+// filesystem path or a base64-encoded payload.
+func (r *DepthAnythingCpp) Predict(opts *pb.PredictOptions) (string, error) {
+	imgs := opts.GetImages()
+	if len(imgs) == 0 {
+		return "", fmt.Errorf("depth-anything-cpp: Predict requires an image in Images[]")
+	}
+
+	imgPath, cleanup, err := materializeImage(imgs[0])
+	if err != nil {
+		return "", fmt.Errorf("depth-anything-cpp: %w", err)
+	}
+	defer cleanup()
+
+	depth, h, w, ext, intr, err := r.runDepthPose(imgPath)
+	if err != nil {
+		return "", err
+	}
+
+	dmin, dmax := minMax(depth)
+	payload, err := json.Marshal(depthResult{
+		DepthW: w, DepthH: h,
+		DepthMin: dmin, DepthMax: dmax,
+		Extrinsics: ext, Intrinsics: intr,
+	})
+	if err != nil {
+		return "", fmt.Errorf("depth-anything-cpp: marshal: %w", err)
+	}
+	return string(payload), nil
+}
+
+// GenerateImage runs depth on req.Src and writes a normalised grayscale depth
+// PNG to req.Dst.
+func (r *DepthAnythingCpp) GenerateImage(req *pb.GenerateImageRequest) error {
+	if req.GetSrc() == "" {
+		return fmt.Errorf("depth-anything-cpp: GenerateImage requires src")
+	}
+	if req.GetDst() == "" {
+		return fmt.Errorf("depth-anything-cpp: GenerateImage requires dst")
+	}
+
+	imgPath, cleanup, err := materializeImage(req.GetSrc())
+	if err != nil {
+		return fmt.Errorf("depth-anything-cpp: %w", err)
+	}
+	defer cleanup()
+
+	depth, h, w, _, _, err := r.runDepthPose(imgPath)
+	if err != nil {
+		return err
+	}
+	return writeDepthPNG(req.GetDst(), depth, h, w)
+}
+
+// Depth is the typed Depth RPC. It runs the Depth Anything 3 pipeline on the
+// request's src image and fills a DepthResponse honoring the include_* flags and
+// exports: per-pixel metric depth + confidence (DualDPT) or depth + sky (mono),
+// camera extrinsics/intrinsics, an optional back-projected 3D point cloud and
+// glb/COLMAP exports. The src may be a filesystem path or a base64 payload.
+func (r *DepthAnythingCpp) Depth(in *pb.DepthRequest) (pb.DepthResponse, error) {
+	// Accumulate into locals and return a single composite literal at the end:
+	// returning a named pb.DepthResponse value would copy its embedded mutex
+	// (go vet copylocks).
+	if r.handle == 0 {
+		return pb.DepthResponse{}, fmt.Errorf("depth-anything-cpp: model not loaded")
+	}
+	if in.GetSrc() == "" {
+		return pb.DepthResponse{}, fmt.Errorf("depth-anything-cpp: Depth requires src")
+	}
+
+	imgPath, cleanup, err := materializeImage(in.GetSrc())
+	if err != nil {
+		return pb.DepthResponse{}, fmt.Errorf("depth-anything-cpp: %w", err)
+	}
+	defer cleanup()
+
+	// Dense per-pixel output + pose. Pass buffer pointers only for the
+	// requested maps so the native side can skip unrequested work; ext/intr
+	// must always point at 12/9 floats per the C ABI.
+	var (
+		h, w, isMetric      int32
+		depthPtr, confPtr   *float32
+		skyPtr              *float32
+		ext                 [12]float32
+		intr                [9]float32
+		pDepth, pConf, pSky **float32
+	)
+	if in.GetIncludeDepth() {
+		pDepth = &depthPtr
+	}
+	if in.GetIncludeConfidence() {
+		pConf = &confPtr
+	}
+	if in.GetIncludeSky() {
+		pSky = &skyPtr
+	}
+
+	rc := CapiDepthDense(r.handle, imgPath, &h, &w, pDepth, pConf, pSky, &ext[0], &intr[0], &isMetric)
+	if rc != 0 {
+		return pb.DepthResponse{}, fmt.Errorf("depth-anything-cpp: da_capi_depth_dense failed (rc=%d): %s", rc, r.lastError())
+	}
+
+	n := int(h) * int(w)
+	var (
+		depth, conf, sky      []float32
+		extrinsics, intrinsic []float32
+		numPoints             int32
+		points                []float32
+		pointColors           []byte
+		exportPaths           []string
+	)
+
+	if depthPtr != nil {
+		depth = copyFloats(depthPtr, n)
+		CapiFreeFloats(depthPtr)
+	}
+	if confPtr != nil {
+		conf = copyFloats(confPtr, n)
+		CapiFreeFloats(confPtr)
+	}
+	if skyPtr != nil {
+		sky = copyFloats(skyPtr, n)
+		CapiFreeFloats(skyPtr)
+	}
+	if in.GetIncludePose() {
+		extrinsics = append([]float32(nil), ext[:]...)
+		intrinsic = append([]float32(nil), intr[:]...)
+	}
+
+	// 3D point cloud (DualDPT / pose-capable models only).
+	if in.GetIncludePoints() {
+		var (
+			np     int32
+			xyzPtr *float32
+			rgbPtr *byte
+		)
+		if rc := CapiPoints(r.handle, imgPath, in.GetPointsConfThresh(), &np, &xyzPtr, &rgbPtr); rc != 0 {
+			return pb.DepthResponse{}, fmt.Errorf("depth-anything-cpp: da_capi_points failed (rc=%d): %s", rc, r.lastError())
+		}
+		numPoints = np
+		if xyzPtr != nil {
+			points = copyFloats(xyzPtr, int(np)*3)
+			CapiFreeFloats(xyzPtr)
+		}
+		if rgbPtr != nil {
+			pointColors = copyBytes(rgbPtr, int(np)*3)
+			CapiFreeBytes(rgbPtr)
+		}
+	}
+
+	// Exports (glb / colmap). They are written under in.Dst (a directory); a
+	// temp dir is used when Dst is empty.
+	if len(in.GetExports()) > 0 {
+		exportPaths, err = r.runExports(imgPath, in.GetDst(), in.GetExports())
+		if err != nil {
+			return pb.DepthResponse{}, err
+		}
+	}
+
+	return pb.DepthResponse{
+		Width:       w,
+		Height:      h,
+		Depth:       depth,
+		Confidence:  conf,
+		Sky:         sky,
+		Extrinsics:  extrinsics,
+		Intrinsics:  intrinsic,
+		NumPoints:   numPoints,
+		Points:      points,
+		PointColors: pointColors,
+		ExportPaths: exportPaths,
+		IsMetric:    isMetric != 0,
+	}, nil
+}
+
+// runExports writes the requested exports for imgPath into dstDir and returns
+// the written paths. Supported exports: "glb", "colmap".
+func (r *DepthAnythingCpp) runExports(imgPath, dstDir string, exports []string) ([]string, error) {
+	if dstDir == "" {
+		tmp, err := os.MkdirTemp("", "depth-anything-export-*")
+		if err != nil {
+			return nil, fmt.Errorf("depth-anything-cpp: mkdir export dir: %w", err)
+		}
+		dstDir = tmp
+	} else if err := os.MkdirAll(dstDir, 0o750); err != nil {
+		return nil, fmt.Errorf("depth-anything-cpp: mkdir %s: %w", dstDir, err)
+	}
+
+	var paths []string
+	for _, exp := range exports {
+		switch exp {
+		case "glb":
+			out := filepath.Join(dstDir, "pointcloud.glb")
+			if rc := CapiExportGlb(r.handle, imgPath, out); rc != 0 {
+				return nil, fmt.Errorf("depth-anything-cpp: da_capi_export_glb failed (rc=%d): %s", rc, r.lastError())
+			}
+			paths = append(paths, out)
+		case "colmap":
+			out := filepath.Join(dstDir, "colmap")
+			if err := os.MkdirAll(out, 0o750); err != nil {
+				return nil, fmt.Errorf("depth-anything-cpp: mkdir %s: %w", out, err)
+			}
+			if rc := CapiExportColmap(r.handle, imgPath, out, 1); rc != 0 {
+				return nil, fmt.Errorf("depth-anything-cpp: da_capi_export_colmap failed (rc=%d): %s", rc, r.lastError())
+			}
+			paths = append(paths, out)
+		default:
+			return nil, fmt.Errorf("depth-anything-cpp: unknown export %q (want glb|colmap)", exp)
+		}
+	}
+	return paths, nil
+}
+
+// copyFloats copies n float32 values from a C heap pointer into a fresh Go
+// slice so the C buffer can be freed afterwards.
+func copyFloats(p *float32, n int) []float32 {
+	if p == nil || n <= 0 {
+		return nil
+	}
+	src := unsafe.Slice(p, n)
+	out := make([]float32, n)
+	copy(out, src)
+	return out
+}
+
+// copyBytes copies n bytes from a C heap pointer into a fresh Go slice.
+func copyBytes(p *byte, n int) []byte {
+	if p == nil || n <= 0 {
+		return nil
+	}
+	src := unsafe.Slice(p, n)
+	out := make([]byte, n)
+	copy(out, src)
+	return out
+}
+
+// runDepthPose runs depth estimation then pose recovery on an image file. It
+// returns the row-major depth map (length h*w), its dimensions, the 3x4
+// extrinsics (12 floats) and 3x3 intrinsics (9 floats).
+// runDepthPose returns depth + camera pose via two C-API calls (depth then pose).
+// For a nested metric model both calls run the full two-branch pipeline, so this
+// path infers twice; the typed Depth RPC (single da_capi_depth_dense call) is the
+// efficient path for nested models.
+func (r *DepthAnythingCpp) runDepthPose(imagePath string) (depth []float32, h, w int, ext [12]float32, intr [9]float32, err error) {
+	if r.handle == 0 {
+		err = fmt.Errorf("depth-anything-cpp: model not loaded")
+		return
+	}
+
+	var ch, cw int32
+	ptr := CapiDepthPath(r.handle, imagePath, &ch, &cw)
+	if ptr == nil {
+		err = fmt.Errorf("depth-anything-cpp: da_capi_depth_path failed: %s", r.lastError())
+		return
+	}
+	h, w = int(ch), int(cw)
+	n := h * w
+	if n > 0 {
+		src := unsafe.Slice(ptr, n)
+		depth = make([]float32, n)
+		copy(depth, src)
+	}
+	CapiFreeFloats(ptr)
+
+	if rc := CapiPosePath(r.handle, imagePath, &ext[0], &intr[0]); rc != 0 {
+		err = fmt.Errorf("depth-anything-cpp: da_capi_pose_path failed (rc=%d): %s", rc, r.lastError())
+		return
+	}
+	return
+}
+
+// lastError returns the context's last error string, or "" if none.
+func (r *DepthAnythingCpp) lastError() string {
+	if CapiLastError == nil || r.handle == 0 {
+		return ""
+	}
+	return CapiLastError(r.handle)
+}
+
+// materializeImage returns a filesystem path for an image argument that may be
+// either an existing path or a base64-encoded payload. When the input is
+// base64 it is decoded into a temp file; cleanup removes it (no-op for a path).
+func materializeImage(arg string) (path string, cleanup func(), err error) {
+	cleanup = func() {}
+	if _, statErr := os.Stat(arg); statErr == nil {
+		return arg, cleanup, nil
+	}
+	// Strip an optional data URL prefix (data:image/...;base64,<payload>).
+	b64 := arg
+	if i := indexComma(b64); i >= 0 && hasDataPrefix(b64) {
+		b64 = b64[i+1:]
+	}
+	data, decErr := base64.StdEncoding.DecodeString(b64)
+	if decErr != nil {
+		return "", cleanup, fmt.Errorf("image is neither an existing path nor valid base64: %v", decErr)
+	}
+	f, tErr := os.CreateTemp("", "depth-anything-*.img")
+	if tErr != nil {
+		return "", cleanup, tErr
+	}
+	if _, wErr := f.Write(data); wErr != nil {
+		_ = f.Close()
+		_ = os.Remove(f.Name())
+		return "", cleanup, wErr
+	}
+	_ = f.Close()
+	name := f.Name()
+	return name, func() { _ = os.Remove(name) }, nil
+}
+
+func hasDataPrefix(s string) bool {
+	return len(s) >= 5 && s[:5] == "data:"
+}
+
+func indexComma(s string) int {
+	for i := 0; i < len(s); i++ {
+		if s[i] == ',' {
+			return i
+		}
+	}
+	return -1
+}
+
+// writeDepthPNG min-max normalises a depth map and writes it as an 8-bit
+// grayscale PNG. Near = bright (255), far = dark (0), matching the usual
+// depth-map convention for inverse-depth-like outputs.
+func writeDepthPNG(dst string, depth []float32, h, w int) error {
+	if h <= 0 || w <= 0 || len(depth) < h*w {
+		return fmt.Errorf("depth-anything-cpp: writeDepthPNG: bad dims h=%d w=%d len=%d", h, w, len(depth))
+	}
+	dmin, dmax := minMax(depth)
+	span := dmax - dmin
+	if span <= 0 || math.IsNaN(float64(span)) {
+		span = 1
+	}
+	img := image.NewGray(image.Rect(0, 0, w, h))
+	for y := 0; y < h; y++ {
+		for x := 0; x < w; x++ {
+			v := depth[y*w+x]
+			n := (v - dmin) / span // 0..1
+			if math.IsNaN(float64(n)) {
+				n = 0
+			}
+			if n < 0 {
+				n = 0
+			} else if n > 1 {
+				n = 1
+			}
+			img.Pix[y*img.Stride+x] = uint8(n * 255)
+		}
+	}
+	// dst is the gRPC-provided output path chosen by the LocalAI core (the
+	// intended write destination for the rendered depth map), not
+	// attacker-controlled input, so the variable path is expected here.
+	f, err := os.Create(dst) // #nosec G304
+	if err != nil {
+		return err
+	}
+	defer func() { _ = f.Close() }()
+	return png.Encode(f, img)
+}
+
+func minMax(v []float32) (mn, mx float32) {
+	if len(v) == 0 {
+		return 0, 0
+	}
+	mn, mx = v[0], v[0]
+	for _, x := range v {
+		if math.IsNaN(float64(x)) || math.IsInf(float64(x), 0) {
+			continue
+		}
+		if x < mn {
+			mn = x
+		}
+		if x > mx {
+			mx = x
+		}
+	}
+	return mn, mx
+}

backend/go/depth-anything-cpp/main.go

@@ -0,0 +1,62 @@
+package main
+
+// main.go - entry point for the depth-anything-cpp gRPC backend.
+//
+// Dlopens libdepthanythingcpp-<variant>.so via purego at the path in
+// DEPTHANYTHING_LIBRARY (set by run.sh based on /proc/cpuinfo), registers the
+// da_capi_* C ABI symbols, then starts the gRPC server.
+
+import (
+	"flag"
+	"os"
+
+	"github.com/ebitengine/purego"
+	grpc "github.com/mudler/LocalAI/pkg/grpc"
+)
+
+var (
+	addr = flag.String("addr", "localhost:50051", "the address to connect to")
+)
+
+type LibFuncs struct {
+	FuncPtr any
+	Name    string
+}
+
+func main() {
+	// Get library name from environment variable, default to fallback
+	libName := os.Getenv("DEPTHANYTHING_LIBRARY")
+	if libName == "" {
+		libName = "./libdepthanythingcpp-fallback.so"
+	}
+
+	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
+	if err != nil {
+		panic(err)
+	}
+
+	libFuncs := []LibFuncs{
+		{&CapiLoad, "da_capi_load"},
+		{&CapiLoadNested, "da_capi_load_nested"},
+		{&CapiFree, "da_capi_free"},
+		{&CapiLastError, "da_capi_last_error"},
+		{&CapiDepthPath, "da_capi_depth_path"},
+		{&CapiFreeFloats, "da_capi_free_floats"},
+		{&CapiPosePath, "da_capi_pose_path"},
+		{&CapiDepthDense, "da_capi_depth_dense"},
+		{&CapiPoints, "da_capi_points"},
+		{&CapiFreeBytes, "da_capi_free_bytes"},
+		{&CapiExportGlb, "da_capi_export_glb"},
+		{&CapiExportColmap, "da_capi_export_colmap"},
+	}
+
+	for _, lf := range libFuncs {
+		purego.RegisterLibFunc(lf.FuncPtr, lib, lf.Name)
+	}
+
+	flag.Parse()
+
+	if err := grpc.StartServer(*addr, &DepthAnythingCpp{}); err != nil {
+		panic(err)
+	}
+}

backend/go/depth-anything-cpp/main_test.go

@@ -0,0 +1,167 @@
+package main
+
+// main_test.go - end-to-end smoke test for the depth-anything-cpp gRPC backend.
+//
+// Spawns the compiled depth-anything-cpp binary on a free local port, dials it
+// via gRPC, and exercises LoadModel + Predict against the test fixtures
+// downloaded by test.sh: the small (vits) f32 GGUF of Depth Anything 3 and a
+// real photo. Asserts that Predict returns a JSON payload with a positive
+// depth-map width/height.
+//
+// The spec Skip()s cleanly if its fixtures (the model, the test image, the
+// built binary, or the fallback .so) are missing, so the test target stays
+// usable on a fresh checkout / on CI runners where the model hasn't been
+// downloaded.
+
+import (
+	"context"
+	"encoding/base64"
+	"encoding/json"
+	"fmt"
+	"net"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"testing"
+	"time"
+
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+	"google.golang.org/grpc"
+	"google.golang.org/grpc/credentials/insecure"
+)
+
+func TestDepth(t *testing.T) {
+	RegisterFailHandler(Fail)
+	RunSpecs(t, "depth-anything-cpp backend smoke suite")
+}
+
+// freePort grabs an ephemeral TCP port and immediately releases it so the
+// spawned backend can bind to it. There is a tiny TOCTOU window here but in
+// practice it's adequate for a smoke test on a quiet runner.
+func freePort() int {
+	l, err := net.Listen("tcp", "127.0.0.1:0")
+	Expect(err).ToNot(HaveOccurred(), "freePort listen")
+	port := l.Addr().(*net.TCPAddr).Port
+	Expect(l.Close()).To(Succeed())
+	return port
+}
+
+// startBackend spawns the depth-anything-cpp binary on the given port and waits
+// until it accepts TCP connections (up to 10s). It mirrors how main.go resolves
+// the purego library: the DEPTHANYTHING_LIBRARY env var points the dlopen at the
+// freshly built fallback .so. The returned cleanup func kills the process.
+func startBackend(port int) func() {
+	binary, err := filepath.Abs("./depth-anything-cpp")
+	Expect(err).ToNot(HaveOccurred())
+	if _, err := os.Stat(binary); err != nil {
+		Skip(fmt.Sprintf("backend binary not built: %s (run `make depth-anything-cpp` first)", binary))
+	}
+
+	libPath, err := filepath.Abs("./libdepthanythingcpp-fallback.so")
+	Expect(err).ToNot(HaveOccurred())
+	if _, err := os.Stat(libPath); err != nil {
+		Skip(fmt.Sprintf("fallback library not built: %s (run `make libdepthanythingcpp-fallback.so` first)", libPath))
+	}
+
+	addr := fmt.Sprintf("127.0.0.1:%d", port)
+	cmd := exec.Command(binary, "--addr", addr)
+	cmd.Env = append(os.Environ(), "DEPTHANYTHING_LIBRARY="+libPath)
+	cmd.Stdout = os.Stderr
+	cmd.Stderr = os.Stderr
+	Expect(cmd.Start()).To(Succeed())
+
+	cleanup := func() {
+		if cmd.Process != nil {
+			_ = cmd.Process.Kill()
+			_, _ = cmd.Process.Wait()
+		}
+	}
+
+	deadline := time.Now().Add(10 * time.Second)
+	for time.Now().Before(deadline) {
+		c, err := net.DialTimeout("tcp", addr, 200*time.Millisecond)
+		if err == nil {
+			_ = c.Close()
+			return cleanup
+		}
+		time.Sleep(200 * time.Millisecond)
+	}
+
+	cleanup()
+	Fail(fmt.Sprintf("backend did not become ready on %s within 10s", addr))
+	return func() {}
+}
+
+// loadTestImage reads the test image downloaded by test.sh and returns its
+// base64-encoded content (one of the wire formats accepted by Predict).
+func loadTestImage() string {
+	imgPath, err := filepath.Abs("test-data/test.jpg")
+	Expect(err).ToNot(HaveOccurred())
+	imgBytes, err := os.ReadFile(imgPath)
+	if err != nil {
+		Skip(fmt.Sprintf("test image not present: %s (run test.sh first)", imgPath))
+	}
+	return base64.StdEncoding.EncodeToString(imgBytes)
+}
+
+// dialBackend opens a gRPC client connection to the spawned backend.
+func dialBackend(port int) (pb.BackendClient, func()) {
+	addr := fmt.Sprintf("127.0.0.1:%d", port)
+	conn, err := grpc.NewClient(addr, grpc.WithTransportCredentials(insecure.NewCredentials()))
+	Expect(err).ToNot(HaveOccurred())
+	return pb.NewBackendClient(conn), func() { _ = conn.Close() }
+}
+
+// modelPathOrSkip resolves the model file under ./test-models/ and Skip()s the
+// current spec if it's missing (not present on a fresh checkout / on CI runners
+// without the download).
+func modelPathOrSkip(name string) string {
+	modelDir, err := filepath.Abs("test-models")
+	Expect(err).ToNot(HaveOccurred())
+	modelPath := filepath.Join(modelDir, name)
+	if _, err := os.Stat(modelPath); err != nil {
+		Skip(fmt.Sprintf("model not present: %s (run test.sh first)", modelPath))
+	}
+	return modelPath
+}
+
+var _ = Describe("depth-anything-cpp backend", func() {
+	It("runs depth+pose against a known-good image", func() {
+		modelPath := modelPathOrSkip("depth-anything-small-f32.gguf")
+		imgB64 := loadTestImage()
+
+		port := freePort()
+		cleanup := startBackend(port)
+		defer cleanup()
+
+		client, closeConn := dialBackend(port)
+		defer closeConn()
+
+		ctx, cancel := context.WithTimeout(context.Background(), 20*time.Minute)
+		defer cancel()
+
+		loadResp, err := client.LoadModel(ctx, &pb.ModelOptions{
+			Model:     "depth-anything-small-f32.gguf",
+			ModelFile: modelPath,
+			Threads:   4,
+		})
+		Expect(err).ToNot(HaveOccurred(), "LoadModel")
+		Expect(loadResp.GetSuccess()).To(BeTrue(), "LoadModel reported failure: %s", loadResp.GetMessage())
+
+		// Predict runs depth+pose and returns the JSON depthResult in Reply.Message.
+		reply, err := client.Predict(ctx, &pb.PredictOptions{
+			Images: []string{imgB64},
+		})
+		Expect(err).ToNot(HaveOccurred(), "Predict")
+
+		var res depthResult
+		Expect(json.Unmarshal(reply.GetMessage(), &res)).To(Succeed(), "Predict returned non-JSON: %q", string(reply.GetMessage()))
+		Expect(res.DepthW).To(BeNumerically(">", 0), "depth width should be positive")
+		Expect(res.DepthH).To(BeNumerically(">", 0), "depth height should be positive")
+
+		_, _ = fmt.Fprintf(GinkgoWriter, "depth OK: %dx%d min=%.3f max=%.3f\n",
+			res.DepthW, res.DepthH, res.DepthMin, res.DepthMax)
+	})
+})

backend/go/depth-anything-cpp/nested_e2e_test.go

@@ -0,0 +1,64 @@
+package main
+
+// nested_e2e_test.go - e2e smoke for the nested two-file metric model. Loads the
+// anyview branch as the main model and points the metric branch via the
+// "metric_model:<file>" option (exactly as the depth-anything-3-nested gallery
+// entry does), then exercises the typed Depth RPC and asserts a metric depth map.
+//
+// Skips cleanly unless both nested GGUFs are present under ./test-models/ and the
+// backend binary + fallback .so are built.
+
+import (
+	"context"
+	"fmt"
+	"path/filepath"
+	"time"
+
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+var _ = Describe("depth-anything-cpp nested metric model", func() {
+	It("loads the two-file pair via the metric_model option and returns metric depth", func() {
+		anyviewPath := modelPathOrSkip("depth-anything-nested-anyview.gguf")
+		_ = modelPathOrSkip("depth-anything-nested-metric.gguf")
+		imgB64 := loadTestImage()
+
+		port := freePort()
+		cleanup := startBackend(port)
+		defer cleanup()
+
+		client, closeConn := dialBackend(port)
+		defer closeConn()
+
+		ctx, cancel := context.WithTimeout(context.Background(), 25*time.Minute)
+		defer cancel()
+
+		loadResp, err := client.LoadModel(ctx, &pb.ModelOptions{
+			Model:     "depth-anything-nested-anyview.gguf",
+			ModelFile: anyviewPath,
+			ModelPath: filepath.Dir(anyviewPath),
+			Options:   []string{"metric_model:depth-anything-nested-metric.gguf"},
+			Threads:   8,
+		})
+		Expect(err).ToNot(HaveOccurred(), "LoadModel(nested)")
+		Expect(loadResp.GetSuccess()).To(BeTrue(), "LoadModel reported failure: %s", loadResp.GetMessage())
+
+		resp, err := client.Depth(ctx, &pb.DepthRequest{
+			Src:          imgB64,
+			IncludeDepth: true,
+			IncludePose:  true,
+		})
+		Expect(err).ToNot(HaveOccurred(), "Depth(nested)")
+		Expect(resp.GetWidth()).To(BeNumerically(">", 0), "depth width")
+		Expect(resp.GetHeight()).To(BeNumerically(">", 0), "depth height")
+		Expect(resp.GetIsMetric()).To(BeTrue(), "nested output must be metric")
+		Expect(len(resp.GetDepth())).To(Equal(int(resp.GetWidth())*int(resp.GetHeight())), "dense depth length")
+		Expect(len(resp.GetExtrinsics())).To(Equal(12), "extrinsics 3x4")
+		Expect(resp.GetIntrinsics()[0]).To(BeNumerically(">", 0), "fx > 0")
+
+		_, _ = fmt.Fprintf(GinkgoWriter, "nested depth OK: %dx%d is_metric=%v fx=%.2f\n",
+			resp.GetWidth(), resp.GetHeight(), resp.GetIsMetric(), resp.GetIntrinsics()[0])
+	})
+})

backend/go/depth-anything-cpp/options_test.go

@@ -0,0 +1,20 @@
+package main
+
+import (
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+var _ = DescribeTable("optionValue",
+	func(opts []string, key, want string) {
+		Expect(optionValue(opts, key)).To(Equal(want))
+	},
+	Entry("present", []string{"foo:bar", "metric_model:m.gguf"}, "metric_model", "m.gguf"),
+	Entry("absent", []string{"foo:bar"}, "metric_model", ""),
+	Entry("nil", []string(nil), "metric_model", ""),
+	Entry("trims space", []string{"metric_model:  m.gguf  "}, "metric_model", "m.gguf"),
+	Entry("value with colon", []string{"metric_model:a:b.gguf"}, "metric_model", "a:b.gguf"),
+	Entry("first wins", []string{"metric_model:first.gguf", "metric_model:second.gguf"}, "metric_model", "first.gguf"),
+	Entry("empty value", []string{"metric_model:"}, "metric_model", ""),
+	Entry("prefix not key", []string{"metric_model_extra:x"}, "metric_model", ""),
+)

backend/go/depth-anything-cpp/package.sh

@@ -0,0 +1,59 @@
+#!/bin/bash
+
+# Script to copy the appropriate libraries based on architecture
+
+set -e
+
+CURDIR=$(dirname "$(realpath $0)")
+REPO_ROOT="${CURDIR}/../../.."
+
+# Create lib directory
+mkdir -p $CURDIR/package/lib
+
+cp -avf $CURDIR/libdepthanythingcpp-*.so $CURDIR/package/
+cp -avf $CURDIR/depth-anything-cpp $CURDIR/package/
+cp -fv $CURDIR/run.sh $CURDIR/package/
+
+# Detect architecture and copy appropriate libraries
+if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
+    # x86_64 architecture
+    echo "Detected x86_64 architecture, copying x86_64 libraries..."
+    cp -arfLv /lib64/ld-linux-x86-64.so.2 $CURDIR/package/lib/ld.so
+    cp -arfLv /lib/x86_64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
+    cp -arfLv /lib/x86_64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
+elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
+    # ARM64 architecture
+    echo "Detected ARM64 architecture, copying ARM64 libraries..."
+    cp -arfLv /lib/ld-linux-aarch64.so.1 $CURDIR/package/lib/ld.so
+    cp -arfLv /lib/aarch64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
+    cp -arfLv /lib/aarch64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
+elif [ $(uname -s) = "Darwin" ]; then
+    echo "Detected Darwin"
+else
+    echo "Error: Could not detect architecture"
+    exit 1
+fi
+
+# Package GPU libraries based on BUILD_TYPE
+GPU_LIB_SCRIPT="${REPO_ROOT}/scripts/build/package-gpu-libs.sh"
+if [ -f "$GPU_LIB_SCRIPT" ]; then
+    echo "Packaging GPU libraries for BUILD_TYPE=${BUILD_TYPE:-cpu}..."
+    source "$GPU_LIB_SCRIPT" "$CURDIR/package/lib"
+    package_gpu_libs
+fi
+
+echo "Packaging completed successfully"
+ls -liah $CURDIR/package/
+ls -liah $CURDIR/package/lib/

backend/go/depth-anything-cpp/run.sh

@@ -0,0 +1,52 @@
+#!/bin/bash
+set -ex
+
+# Get the absolute current dir where the script is located
+CURDIR=$(dirname "$(realpath $0)")
+
+cd /
+
+echo "CPU info:"
+if [ "$(uname)" != "Darwin" ]; then
+	grep -e "model\sname" /proc/cpuinfo | head -1
+	grep -e "flags" /proc/cpuinfo | head -1
+fi
+
+LIBRARY="$CURDIR/libdepthanythingcpp-fallback.so"
+
+if [ "$(uname)" != "Darwin" ]; then
+	if grep -q -e "\savx\s" /proc/cpuinfo ; then
+		echo "CPU:    AVX    found OK"
+		if [ -e $CURDIR/libdepthanythingcpp-avx.so ]; then
+			LIBRARY="$CURDIR/libdepthanythingcpp-avx.so"
+		fi
+	fi
+
+	if grep -q -e "\savx2\s" /proc/cpuinfo ; then
+		echo "CPU:    AVX2   found OK"
+		if [ -e $CURDIR/libdepthanythingcpp-avx2.so ]; then
+			LIBRARY="$CURDIR/libdepthanythingcpp-avx2.so"
+		fi
+	fi
+
+	# Check avx 512
+	if grep -q -e "\savx512f\s" /proc/cpuinfo ; then
+		echo "CPU:    AVX512F found OK"
+		if [ -e $CURDIR/libdepthanythingcpp-avx512.so ]; then
+			LIBRARY="$CURDIR/libdepthanythingcpp-avx512.so"
+		fi
+	fi
+fi
+
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
+export DEPTHANYTHING_LIBRARY=$LIBRARY
+
+# If there is a lib/ld.so, use it
+if [ -f $CURDIR/lib/ld.so ]; then
+	echo "Using lib/ld.so"
+	echo "Using library: $LIBRARY"
+	exec $CURDIR/lib/ld.so $CURDIR/depth-anything-cpp "$@"
+fi
+
+echo "Using library: $LIBRARY"
+exec $CURDIR/depth-anything-cpp "$@"

backend/go/depth-anything-cpp/test.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+set -e
+
+CURDIR=$(dirname "$(realpath $0)")
+
+echo "Running depth-anything-cpp backend tests..."
+
+# Test model from the mudler/depth-anything.cpp-gguf HuggingFace repo. The small
+# (vits) f32 GGUF is the lightest backbone (~131 MB), so it keeps the download
+# cheap. It is resumed with `curl -C -` and skipped entirely if already present.
+DEPTHANYTHING_MODEL_DIR="${DEPTHANYTHING_MODEL_DIR:-$CURDIR/test-models}"
+
+DEPTHANYTHING_MODEL_FILE="${DEPTHANYTHING_MODEL_FILE:-depth-anything-small-f32.gguf}"
+DEPTHANYTHING_MODEL_URL="${DEPTHANYTHING_MODEL_URL:-https://huggingface.co/mudler/depth-anything.cpp-gguf/resolve/main/depth-anything-small-f32.gguf}"
+
+mkdir -p "$DEPTHANYTHING_MODEL_DIR"
+
+if [ ! -f "$DEPTHANYTHING_MODEL_DIR/$DEPTHANYTHING_MODEL_FILE" ]; then
+    echo "Downloading depth-anything small f32 model (~131 MB)..."
+    # -C - resumes a partial download so an interrupted run doesn't restart from 0.
+    curl -L -C - -o "$DEPTHANYTHING_MODEL_DIR/$DEPTHANYTHING_MODEL_FILE" "$DEPTHANYTHING_MODEL_URL" --progress-bar
+fi
+
+# Use a real photo (people + cars) from the upstream rf-detr.cpp repo (~46 KB).
+# Depth estimation needs real content; a synthetic image would be degenerate.
+TEST_IMAGE_DIR="$CURDIR/test-data"
+TEST_IMAGE_FILE="$TEST_IMAGE_DIR/test.jpg"
+TEST_IMAGE_URL="${TEST_IMAGE_URL:-https://raw.githubusercontent.com/mudler/rf-detr.cpp/main/tests/fixtures/ci/test_image.jpg}"
+
+mkdir -p "$TEST_IMAGE_DIR"
+if [ ! -f "$TEST_IMAGE_FILE" ]; then
+    echo "Downloading test image..."
+    curl -L -o "$TEST_IMAGE_FILE" "$TEST_IMAGE_URL" --progress-bar
+fi
+
+echo "depth-anything-cpp test setup complete."
+echo "  model:      $DEPTHANYTHING_MODEL_DIR/$DEPTHANYTHING_MODEL_FILE"
+echo "  test image: $TEST_IMAGE_FILE"
+
+# Run the Go smoke test: spawns the backend binary on a free port, calls
+# LoadModel + Predict via gRPC against the downloaded GGUF + image.
+echo ""
+echo "Running Go smoke test..."
+cd "$CURDIR"
+go test -v -timeout 30m ./...

backend/go/locate-anything-cpp/Makefile

@@ -10,7 +10,7 @@ JOBS?=$(shell nproc --ignore=1)
 # this on `master` always picks up the latest C-API surface (incl. the
 # per-detection accessor functions used by golocateanythingcpp.go).
 LOCATEANYTHING_REPO?=https://github.com/mudler/locate-anything.cpp.git
-LOCATEANYTHING_VERSION?=60e450945476d5e97e0754a8c0e71a9ea81690e0
+LOCATEANYTHING_VERSION?=92c1682da792c1e8a5dec91acc2be4b02c742ded
 
 ifeq ($(NATIVE),false)
 	CMAKE_ARGS+=-DGGML_NATIVE=OFF

backend/go/omnivoice-cpp/.gitignore

@@ -0,0 +1,17 @@
+# Fetched upstream sources
+sources/
+
+# CMake build directories
+build*/
+
+# Compiled shared libraries
+*.so
+
+# Compiled backend binary
+omnivoice-cpp
+
+# Packaging output
+package/
+
+# Downloaded e2e models
+omnivoice-models/

backend/go/omnivoice-cpp/CMakeLists.txt

@@ -0,0 +1,53 @@
+cmake_minimum_required(VERSION 3.14)
+project(gomnivoicecpp LANGUAGES C CXX)
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
+
+set(OMNIVOICE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/sources/omnivoice.cpp)
+
+# Override upstream's CMAKE_CUDA_ARCHITECTURES before add_subdirectory.
+if(NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
+    set(CMAKE_CUDA_ARCHITECTURES "75-virtual;80-virtual;86-real;89-real")
+endif()
+
+# Add the upstream project. Its own CMakeLists adds ggml + builds
+# omnivoice-core (STATIC, contains src/omnivoice.cpp i.e. the ov_* impl).
+# EXCLUDE_FROM_ALL keeps its CLI tools/tests from building unless referenced.
+add_subdirectory(${OMNIVOICE_DIR} omnivoice EXCLUDE_FROM_ALL)
+
+# Upstream generates version.h into its own CMAKE_CURRENT_BINARY_DIR and adds
+# the top-level ${CMAKE_BINARY_DIR} to omnivoice-core's include path. When the
+# project is nested under add_subdirectory those two directories differ
+# (<build>/omnivoice vs <build>), so omnivoice.cpp cannot find version.h. Point
+# omnivoice-core at the subproject binary dir where version.h is actually
+# generated. (Fix lives here, never in the fetched upstream checkout.)
+target_include_directories(omnivoice-core PRIVATE ${CMAKE_BINARY_DIR}/omnivoice)
+
+add_library(gomnivoicecpp MODULE cpp/gomnivoicecpp.cpp)
+target_link_libraries(gomnivoicecpp PRIVATE omnivoice-core)
+
+target_include_directories(gomnivoicecpp PRIVATE ${OMNIVOICE_DIR}/src)
+target_include_directories(gomnivoicecpp SYSTEM PRIVATE ${OMNIVOICE_DIR}/ggml/include)
+
+# Link GPU backends if the upstream ggml created them.
+foreach(backend blas cuda metal vulkan sycl)
+    if(TARGET ggml-${backend})
+        target_link_libraries(gomnivoicecpp PRIVATE ggml-${backend})
+        if(backend STREQUAL "cuda")
+            find_package(CUDAToolkit QUIET)
+            if(CUDAToolkit_FOUND)
+                target_link_libraries(gomnivoicecpp PRIVATE CUDA::cudart)
+            endif()
+        endif()
+    endif()
+endforeach()
+
+if(MSVC)
+    target_compile_options(gomnivoicecpp PRIVATE /W4 /wd4100 /wd4505)
+else()
+    target_compile_options(gomnivoicecpp PRIVATE -Wall -Wextra
+                          -Wno-unused-parameter -Wno-unused-function)
+endif()
+
+set_property(TARGET gomnivoicecpp PROPERTY CXX_STANDARD 17)
+set_target_properties(gomnivoicecpp PROPERTIES LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})

backend/go/omnivoice-cpp/Makefile

@@ -0,0 +1,122 @@
+CMAKE_ARGS?=
+BUILD_TYPE?=
+NATIVE?=false
+
+GOCMD?=go
+GO_TAGS?=
+JOBS?=$(shell nproc --ignore=1)
+
+# omnivoice.cpp version
+OMNIVOICE_REPO?=https://github.com/ServeurpersoCom/omnivoice.cpp
+OMNIVOICE_VERSION?=2603355a5dfacae5cfc33531d5d0933221843509
+SO_TARGET?=libgomnivoicecpp.so
+
+CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
+
+ifeq ($(NATIVE),false)
+	CMAKE_ARGS+=-DGGML_NATIVE=OFF
+endif
+
+ifeq ($(BUILD_TYPE),cublas)
+	CMAKE_ARGS+=-DGGML_CUDA=ON
+else ifeq ($(BUILD_TYPE),openblas)
+	CMAKE_ARGS+=-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
+else ifeq ($(BUILD_TYPE),clblas)
+	CMAKE_ARGS+=-DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
+else ifeq ($(BUILD_TYPE),hipblas)
+	CMAKE_ARGS+=-DGGML_HIPBLAS=ON
+else ifeq ($(BUILD_TYPE),vulkan)
+	CMAKE_ARGS+=-DGGML_VULKAN=ON
+else ifeq ($(OS),Darwin)
+	ifneq ($(BUILD_TYPE),metal)
+		CMAKE_ARGS+=-DGGML_METAL=OFF
+	else
+		CMAKE_ARGS+=-DGGML_METAL=ON
+		CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=ON
+	endif
+endif
+
+ifeq ($(BUILD_TYPE),sycl_f16)
+	CMAKE_ARGS+=-DGGML_SYCL=ON \
+		-DCMAKE_C_COMPILER=icx \
+		-DCMAKE_CXX_COMPILER=icpx \
+		-DGGML_SYCL_F16=ON
+endif
+
+ifeq ($(BUILD_TYPE),sycl_f32)
+	CMAKE_ARGS+=-DGGML_SYCL=ON \
+		-DCMAKE_C_COMPILER=icx \
+		-DCMAKE_CXX_COMPILER=icpx
+endif
+
+sources/omnivoice.cpp:
+	mkdir -p sources/omnivoice.cpp
+	cd sources/omnivoice.cpp && \
+	git init && \
+	git remote add origin $(OMNIVOICE_REPO) && \
+	git fetch origin && \
+	git checkout $(OMNIVOICE_VERSION) && \
+	git submodule update --init --recursive --depth 1 --single-branch
+
+# Detect OS
+UNAME_S := $(shell uname -s)
+
+# Only build CPU variants on Linux
+ifeq ($(UNAME_S),Linux)
+	VARIANT_TARGETS = libgomnivoicecpp-avx.so libgomnivoicecpp-avx2.so libgomnivoicecpp-avx512.so libgomnivoicecpp-fallback.so
+else
+	VARIANT_TARGETS = libgomnivoicecpp-fallback.so
+endif
+
+omnivoice-cpp: main.go gomnivoicecpp.go $(VARIANT_TARGETS)
+	CGO_ENABLED=0 $(GOCMD) build -tags "$(GO_TAGS)" -o omnivoice-cpp ./
+
+package: omnivoice-cpp
+	bash package.sh
+
+build: package
+
+clean: purge
+	rm -rf libgomnivoicecpp*.so package sources/omnivoice.cpp omnivoice-cpp
+
+purge:
+	rm -rf build*
+
+.NOTPARALLEL:
+
+ifeq ($(UNAME_S),Linux)
+libgomnivoicecpp-avx.so: sources/omnivoice.cpp
+	$(info ${GREEN}I omnivoice-cpp build info:avx${RESET})
+	SO_TARGET=libgomnivoicecpp-avx.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgomnivoicecpp-custom
+	rm -rf build-libgomnivoicecpp-avx.so
+
+libgomnivoicecpp-avx2.so: sources/omnivoice.cpp
+	$(info ${GREEN}I omnivoice-cpp build info:avx2${RESET})
+	SO_TARGET=libgomnivoicecpp-avx2.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) libgomnivoicecpp-custom
+	rm -rf build-libgomnivoicecpp-avx2.so
+
+libgomnivoicecpp-avx512.so: sources/omnivoice.cpp
+	$(info ${GREEN}I omnivoice-cpp build info:avx512${RESET})
+	SO_TARGET=libgomnivoicecpp-avx512.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=on -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) libgomnivoicecpp-custom
+	rm -rf build-libgomnivoicecpp-avx512.so
+endif
+
+libgomnivoicecpp-fallback.so: sources/omnivoice.cpp
+	$(info ${GREEN}I omnivoice-cpp build info:fallback${RESET})
+	SO_TARGET=libgomnivoicecpp-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgomnivoicecpp-custom
+	rm -rf build-libgomnivoicecpp-fallback.so
+
+libgomnivoicecpp-custom: CMakeLists.txt cpp/gomnivoicecpp.cpp cpp/gomnivoicecpp.h
+	mkdir -p build-$(SO_TARGET) && \
+	cd build-$(SO_TARGET) && \
+	cmake .. $(CMAKE_ARGS) && \
+	cmake --build . --config Release -j$(JOBS) --target gomnivoicecpp && \
+	cd .. && \
+	mv build-$(SO_TARGET)/libgomnivoicecpp.so ./$(SO_TARGET)
+
+test: omnivoice-cpp
+	@echo "Running omnivoice-cpp tests..."
+	bash test.sh
+	@echo "omnivoice-cpp tests completed."
+
+all: omnivoice-cpp package

backend/go/omnivoice-cpp/audio.go

@@ -0,0 +1,129 @@
+package main
+
+import (
+	"bytes"
+	"encoding/binary"
+	"fmt"
+	"os"
+	"runtime"
+
+	"github.com/go-audio/audio"
+	"github.com/go-audio/wav"
+)
+
+const omnivoiceSampleRate = 24000
+
+// wavHeader24k returns a 44-byte WAV header for a streaming 24 kHz mono 16-bit
+// PCM stream, with placeholder (0xFFFFFFFF) sizes since the total length is
+// unknown up front. Emitted as the first chunk of TTSStream so the HTTP layer
+// receives a self-describing WAV (the gRPC TTSStream path never sets Message,
+// so the backend owns the header - see core/backend/tts.go:ModelTTSStream).
+func wavHeader24k() []byte {
+	var buf bytes.Buffer
+	w := func(v any) { _ = binary.Write(&buf, binary.LittleEndian, v) }
+	buf.WriteString("RIFF")
+	w(uint32(0xFFFFFFFF))
+	buf.WriteString("WAVE")
+	buf.WriteString("fmt ")
+	w(uint32(16))                      // Subchunk1Size
+	w(uint16(1))                       // PCM
+	w(uint16(1))                       // mono
+	w(uint32(omnivoiceSampleRate))     // sample rate
+	w(uint32(omnivoiceSampleRate * 2)) // byte rate = SR * blockAlign
+	w(uint16(2))                       // block align (16-bit mono)
+	w(uint16(16))                      // bits per sample
+	buf.WriteString("data")
+	w(uint32(0xFFFFFFFF))
+	return buf.Bytes()
+}
+
+// floatToPCM16LE clamps each sample to [-1,1] and encodes it as little-endian
+// signed 16-bit PCM.
+func floatToPCM16LE(samples []float32) []byte {
+	out := make([]byte, len(samples)*2)
+	for i, s := range samples {
+		if s > 1 {
+			s = 1
+		} else if s < -1 {
+			s = -1
+		}
+		v := int16(s * 32767)
+		out[i*2] = byte(v)
+		out[i*2+1] = byte(v >> 8)
+	}
+	return out
+}
+
+// writeWAV24k writes samples as a finalized 24 kHz mono 16-bit WAV at dst.
+func writeWAV24k(dst string, samples []float32) error {
+	f, err := os.Create(dst)
+	if err != nil {
+		return fmt.Errorf("omnivoice: create %q: %w", dst, err)
+	}
+	enc := wav.NewEncoder(f, omnivoiceSampleRate, 16, 1, 1)
+	ints := make([]int, len(samples))
+	for i, s := range samples {
+		if s > 1 {
+			s = 1
+		} else if s < -1 {
+			s = -1
+		}
+		ints[i] = int(s * 32767)
+	}
+	b := &audio.IntBuffer{
+		Format:         &audio.Format{NumChannels: 1, SampleRate: omnivoiceSampleRate},
+		Data:           ints,
+		SourceBitDepth: 16,
+	}
+	if err := enc.Write(b); err != nil {
+		_ = enc.Close()
+		_ = f.Close()
+		return fmt.Errorf("omnivoice: encode WAV: %w", err)
+	}
+	if err := enc.Close(); err != nil {
+		_ = f.Close()
+		return fmt.Errorf("omnivoice: finalize WAV: %w", err)
+	}
+	return f.Close()
+}
+
+// readWAVAsFloat decodes a WAV file (any sample rate/channels) to a mono
+// float32 slice in [-1,1] for use as reference audio. OmniVoice expects 24 kHz;
+// callers should supply 24 kHz reference clips.
+func readWAVAsFloat(path string) ([]float32, error) {
+	f, err := os.Open(path)
+	if err != nil {
+		return nil, fmt.Errorf("omnivoice: open ref %q: %w", path, err)
+	}
+	defer func() { _ = f.Close() }()
+
+	dec := wav.NewDecoder(f)
+	buf, err := dec.FullPCMBuffer()
+	if err != nil {
+		return nil, fmt.Errorf("omnivoice: decode ref %q: %w", path, err)
+	}
+	ch := int(buf.Format.NumChannels)
+	if ch < 1 {
+		ch = 1
+	}
+	bitDepth := int(buf.SourceBitDepth)
+	if bitDepth == 0 {
+		bitDepth = 16
+	}
+	scale := float32(int64(1) << uint(bitDepth-1))
+	n := len(buf.Data) / ch
+	out := make([]float32, n)
+	for i := 0; i < n; i++ {
+		// Downmix to mono by averaging channels.
+		var acc int
+		for c := 0; c < ch; c++ {
+			acc += buf.Data[i*ch+c]
+		}
+		out[i] = float32(acc) / float32(ch) / scale
+	}
+	return out, nil
+}
+
+// runtimeKeepAlive prevents the GC from reclaiming the reference-audio slice
+// while its backing pointer is in use across the C call.
+func runtimeKeepAlive(v any) { runtime.KeepAlive(v) }

backend/go/omnivoice-cpp/cpp/gomnivoicecpp.cpp

@@ -0,0 +1,166 @@
+#include "gomnivoicecpp.h"
+#include "ggml-backend.h"
+#include "omnivoice.h"
+
+#include <cstdio>
+#include <cstdlib>
+#include <cstring>
+
+static ov_context *g_ctx = nullptr;
+
+static void ggml_log_cb(enum ggml_log_level level, const char *log,
+                        void * /*data*/) {
+    if (!log)
+        return;
+    const char *lvl = "?????";
+    switch (level) {
+    case GGML_LOG_LEVEL_DEBUG: lvl = "DEBUG"; break;
+    case GGML_LOG_LEVEL_INFO:  lvl = "INFO";  break;
+    case GGML_LOG_LEVEL_WARN:  lvl = "WARN";  break;
+    case GGML_LOG_LEVEL_ERROR: lvl = "ERROR"; break;
+    default: break;
+    }
+    fprintf(stderr, "[%-5s] %s", lvl, log);
+    fflush(stderr);
+}
+
+int omni_load(const char *model_path, const char *codec_path, int use_fa,
+              int clamp_fp16) {
+    ggml_log_set(ggml_log_cb, nullptr);
+    ggml_backend_load_all();
+
+    if (!model_path || model_path[0] == '\0') {
+        fprintf(stderr, "[omnivoice-cpp] ERROR: model_path is required\n");
+        return 1;
+    }
+    if (!codec_path || codec_path[0] == '\0') {
+        fprintf(stderr, "[omnivoice-cpp] ERROR: codec_path is required\n");
+        return 2;
+    }
+
+    ov_init_params p;
+    ov_init_default_params(&p);
+    p.model_path = model_path;
+    p.codec_path = codec_path;
+    p.use_fa = use_fa != 0;
+    p.clamp_fp16 = clamp_fp16 != 0;
+
+    fprintf(stderr, "[omnivoice-cpp] Loading model=%s codec=%s\n", model_path,
+            codec_path);
+
+    g_ctx = ov_init(&p);
+    if (!g_ctx) {
+        fprintf(stderr, "[omnivoice-cpp] FATAL: ov_init failed: %s\n",
+                ov_last_error());
+        return 3;
+    }
+    fprintf(stderr, "[omnivoice-cpp] Model loaded (%s)\n", ov_version());
+    return 0;
+}
+
+// Fill an ov_tts_params from the flat wrapper arguments.
+static void fill_params(ov_tts_params *tp, const char *text, const char *lang,
+                        const char *instruct, const float *ref_samples,
+                        int ref_n, const char *ref_text, long long seed,
+                        int denoise) {
+    ov_tts_default_params(tp);
+    tp->text = text ? text : "";
+    tp->lang = lang ? lang : "";
+    if (instruct && instruct[0] != '\0')
+        tp->instruct = instruct;
+    if (ref_samples && ref_n > 0) {
+        tp->ref_audio_24k = ref_samples;
+        tp->ref_n_samples = ref_n;
+        if (ref_text && ref_text[0] != '\0')
+            tp->ref_text = ref_text;
+        tp->denoise = denoise != 0;
+    }
+    if (seed >= 0)
+        tp->mg_seed = (uint64_t)seed;
+}
+
+float *omni_tts(const char *text, const char *lang, const char *instruct,
+                const float *ref_samples, int ref_n, const char *ref_text,
+                long long seed, int denoise, int *out_n) {
+    if (out_n)
+        *out_n = 0;
+    if (!g_ctx) {
+        fprintf(stderr, "[omnivoice-cpp] ERROR: model not loaded\n");
+        return nullptr;
+    }
+    if (!text || text[0] == '\0') {
+        fprintf(stderr, "[omnivoice-cpp] ERROR: text is required\n");
+        return nullptr; // omni_tts: out_n already 0
+    }
+    ov_tts_params tp;
+    fill_params(&tp, text, lang, instruct, ref_samples, ref_n, ref_text, seed,
+                denoise);
+
+    ov_audio out = {0};
+    enum ov_status rc = ov_synthesize(g_ctx, &tp, &out);
+    if (rc != OV_STATUS_OK || out.n_samples <= 0 || !out.samples) {
+        fprintf(stderr, "[omnivoice-cpp] ERROR: synthesize failed (rc=%d): %s\n",
+                (int)rc, ov_last_error());
+        ov_audio_free(&out);
+        return nullptr;
+    }
+
+    // Copy into a plain malloc buffer the Go side can free symmetrically via
+    // omni_pcm_free; then release the ov_audio-owned buffer.
+    size_t bytes = (size_t)out.n_samples * sizeof(float);
+    float *buf = (float *)malloc(bytes);
+    if (!buf) {
+        fprintf(stderr, "[omnivoice-cpp] ERROR: malloc(%zu) failed\n", bytes);
+        ov_audio_free(&out);
+        return nullptr;
+    }
+    memcpy(buf, out.samples, bytes);
+    if (out_n)
+        *out_n = out.n_samples;
+    ov_audio_free(&out);
+    return buf;
+}
+
+int omni_tts_stream(const char *text, const char *lang, const char *instruct,
+                    const float *ref_samples, int ref_n, const char *ref_text,
+                    long long seed, int denoise, omni_pcm_chunk_cb cb,
+                    void *user_data) {
+    if (!g_ctx) {
+        fprintf(stderr, "[omnivoice-cpp] ERROR: model not loaded\n");
+        return 1;
+    }
+    if (!cb) {
+        fprintf(stderr, "[omnivoice-cpp] ERROR: stream callback is null\n");
+        return 2;
+    }
+    if (!text || text[0] == '\0') {
+        fprintf(stderr, "[omnivoice-cpp] ERROR: text is required\n");
+        return 4;
+    }
+    ov_tts_params tp;
+    fill_params(&tp, text, lang, instruct, ref_samples, ref_n, ref_text, seed,
+                denoise);
+    // ov_audio_chunk_cb has the identical signature to omni_pcm_chunk_cb
+    // (bool vs int return are ABI-compatible; non-zero == true).
+    tp.on_chunk = (ov_audio_chunk_cb)cb;
+    tp.on_chunk_user_data = user_data;
+
+    ov_audio out = {0}; // stays empty in streaming mode
+    enum ov_status rc = ov_synthesize(g_ctx, &tp, &out);
+    ov_audio_free(&out);
+    if (rc != OV_STATUS_OK && rc != OV_STATUS_CANCELLED) {
+        fprintf(stderr, "[omnivoice-cpp] ERROR: stream synth failed (rc=%d): %s\n",
+                (int)rc, ov_last_error());
+        return 3;
+    }
+    return 0;
+}
+
+void omni_pcm_free(float *p) { free(p); }
+
+void omni_unload(void) {
+    if (g_ctx) {
+        ov_free(g_ctx);
+        g_ctx = nullptr;
+    }
+}

backend/go/omnivoice-cpp/cpp/gomnivoicecpp.h

@@ -0,0 +1,38 @@
+#pragma once
+
+#include <cstdint>
+
+extern "C" {
+
+// Streaming PCM chunk callback. samples is mono float PCM at 24 kHz, valid
+// only for the duration of the call. Return non-zero to continue, 0 to abort.
+typedef int (*omni_pcm_chunk_cb)(const float *samples, int n_samples,
+                                 void *user_data);
+
+// Load the LM (model_path) + codec (codec_path) GGUFs. use_fa / clamp_fp16
+// map to ov_init_params. Returns 0 on success, non-zero on failure.
+int omni_load(const char *model_path, const char *codec_path, int use_fa,
+              int clamp_fp16);
+
+// Synthesize to a malloc'd float PCM buffer (caller frees via omni_pcm_free).
+// ref_samples != null && ref_n > 0 => voice cloning (ref_text optional).
+// instruct != null && non-empty => voice design. seed < 0 keeps the default
+// MaskGIT seed. denoise toggles the <|denoise|> marker (only with a reference).
+// Writes the sample count to *out_n. Returns NULL on failure (out_n set to 0).
+float *omni_tts(const char *text, const char *lang, const char *instruct,
+                const float *ref_samples, int ref_n, const char *ref_text,
+                long long seed, int denoise, int *out_n);
+
+// Streaming synthesis: cb is invoked per PCM chunk as audio is produced.
+// Same reference/design/seed semantics as omni_tts. Returns 0 on success.
+int omni_tts_stream(const char *text, const char *lang, const char *instruct,
+                    const float *ref_samples, int ref_n, const char *ref_text,
+                    long long seed, int denoise, omni_pcm_chunk_cb cb,
+                    void *user_data);
+
+// Free a buffer returned by omni_tts.
+void omni_pcm_free(float *p);
+
+// Release the OmniVoice context.
+void omni_unload(void);
+}

backend/go/omnivoice-cpp/e2e_test.go

@@ -0,0 +1,74 @@
+package main
+
+import (
+	"os"
+	"strings"
+
+	"github.com/ebitengine/purego"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+func ttsReq(text, voice string, lang *string, dst string) *pb.TTSRequest {
+	return &pb.TTSRequest{Text: text, Voice: voice, Language: lang, Dst: dst}
+}
+
+var _ = Describe("OmniVoice e2e", Label("e2e"), func() {
+	var loaded bool
+
+	BeforeEach(func() {
+		modelPath := os.Getenv("OMNIVOICE_MODEL")
+		codecPath := os.Getenv("OMNIVOICE_CODEC")
+		if modelPath == "" || codecPath == "" {
+			Skip("OMNIVOICE_MODEL / OMNIVOICE_CODEC not set; skipping e2e")
+		}
+		if !loaded {
+			lib := os.Getenv("OMNIVOICE_LIBRARY")
+			if lib == "" {
+				lib = "./libgomnivoicecpp-fallback.so"
+			}
+			h, err := purego.Dlopen(lib, purego.RTLD_NOW|purego.RTLD_GLOBAL)
+			Expect(err).ToNot(HaveOccurred())
+			purego.RegisterLibFunc(&CppLoad, h, "omni_load")
+			purego.RegisterLibFunc(&CppTTS, h, "omni_tts")
+			purego.RegisterLibFunc(&CppTTSStream, h, "omni_tts_stream")
+			purego.RegisterLibFunc(&CppPCMFree, h, "omni_pcm_free")
+			purego.RegisterLibFunc(&CppUnload, h, "omni_unload")
+			Expect(CppLoad(modelPath, codecPath, 0, 0)).To(Equal(0))
+			loaded = true
+		}
+	})
+
+	It("synthesizes a WAV file via TTS", func() {
+		b := &OmnivoiceCpp{opts: loadOptions{seed: 42, denoise: true}}
+		dst := GinkgoT().TempDir() + "/out.wav"
+		lang := "en"
+		err := b.TTS(ttsReq("Hello world.", "", &lang, dst))
+		Expect(err).ToNot(HaveOccurred())
+		fi, err := os.Stat(dst)
+		Expect(err).ToNot(HaveOccurred())
+		Expect(fi.Size()).To(BeNumerically(">", int64(44)))
+	})
+
+	It("streams audio chunks via TTSStream", func() {
+		b := &OmnivoiceCpp{opts: loadOptions{seed: 42, denoise: true}}
+		results := make(chan []byte, 1024)
+		lang := "en"
+		done := make(chan error, 1)
+		go func() { done <- b.TTSStream(ttsReq("Hello there, streaming test.", "", &lang, ""), results) }()
+
+		var chunks int
+		var first []byte
+		for c := range results {
+			if chunks == 0 {
+				first = c
+			}
+			chunks++
+		}
+		Expect(<-done).ToNot(HaveOccurred())
+		Expect(chunks).To(BeNumerically(">=", 2))
+		Expect(string(first[0:4])).To(Equal("RIFF"))
+		Expect(strings.HasPrefix(string(first[8:12]), "WAVE")).To(BeTrue())
+	})
+})

backend/go/omnivoice-cpp/gomnivoicecpp.go

@@ -0,0 +1,246 @@
+package main
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"sync"
+	"unsafe"
+
+	"github.com/ebitengine/purego"
+	"github.com/mudler/LocalAI/pkg/grpc/base"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+)
+
+var (
+	// omni_load(model_path, codec_path, use_fa, clamp_fp16) int
+	CppLoad func(modelPath, codecPath string, useFA, clampFP16 int) int
+	// omni_tts(text, lang, instruct, ref_samples, ref_n, ref_text, seed, denoise, out_n) -> float* (uintptr)
+	CppTTS func(text, lang, instruct string, refSamples unsafe.Pointer, refN int,
+		refText string, seed int64, denoise int, outN unsafe.Pointer) uintptr
+	// omni_tts_stream(text, lang, instruct, ref_samples, ref_n, ref_text, seed, denoise, cb, user) int
+	CppTTSStream func(text, lang, instruct string, refSamples unsafe.Pointer, refN int,
+		refText string, seed int64, denoise int, cb uintptr, user uintptr) int
+	CppPCMFree func(ptr uintptr)
+	CppUnload  func()
+)
+
+type OmnivoiceCpp struct {
+	base.SingleThread
+	opts loadOptions
+	// audioPath is the model-config reference voice (tts.audio_path), used as
+	// the default voice-cloning reference when a request does not set Voice.
+	audioPath string
+}
+
+func (o *OmnivoiceCpp) Load(opts *pb.ModelOptions) error {
+	model := opts.ModelFile
+	if model == "" {
+		model = opts.ModelPath
+	}
+	if !filepath.IsAbs(model) && opts.ModelPath != "" {
+		model = filepath.Join(opts.ModelPath, model)
+	}
+
+	o.opts = parseOptions(opts.Options)
+
+	// Resolve the codec/tokenizer GGUF: explicit option, else auto-discover a
+	// *tokenizer*.gguf sibling of the base model.
+	codec := o.opts.codecPath
+	if codec != "" && !filepath.IsAbs(codec) {
+		codec = filepath.Join(filepath.Dir(model), codec)
+	}
+	if codec == "" {
+		codec = discoverTokenizer(filepath.Dir(model))
+	}
+	if codec == "" {
+		return fmt.Errorf("omnivoice: no codec/tokenizer GGUF found; set option 'tokenizer:<file>'")
+	}
+	o.opts.codecPath = codec
+
+	// tts.audio_path (ModelOptions.AudioPath) is the config-level voice-cloning
+	// reference: a default reference WAV used when a request omits Voice.
+	// Resolved relative to the model directory like the codec.
+	o.audioPath = opts.AudioPath
+	if o.audioPath != "" && !filepath.IsAbs(o.audioPath) {
+		o.audioPath = filepath.Join(filepath.Dir(model), o.audioPath)
+	}
+
+	useFA := boolToInt(o.opts.useFA)
+	clamp := boolToInt(o.opts.clampFP16)
+
+	fmt.Fprintf(os.Stderr, "[omnivoice-cpp] Load model=%s codec=%s use_fa=%d clamp_fp16=%d\n",
+		model, codec, useFA, clamp)
+
+	if rc := CppLoad(model, codec, useFA, clamp); rc != 0 {
+		return fmt.Errorf("omnivoice: failed to load model (rc=%d)", rc)
+	}
+	return nil
+}
+
+// discoverTokenizer returns the first *tokenizer*.gguf in dir, or "".
+func discoverTokenizer(dir string) string {
+	entries, err := os.ReadDir(dir)
+	if err != nil {
+		return ""
+	}
+	for _, e := range entries {
+		name := strings.ToLower(e.Name())
+		if strings.Contains(name, "tokenizer") && strings.HasSuffix(name, ".gguf") {
+			return filepath.Join(dir, e.Name())
+		}
+	}
+	return ""
+}
+
+func boolToInt(b bool) int {
+	if b {
+		return 1
+	}
+	return 0
+}
+
+// refAudio loads the reference WAV (voice cloning) if voice points to a file.
+// Returns nil if no cloning (empty or non-path - voice design uses Instructions).
+func (o *OmnivoiceCpp) refAudio(voice string) ([]float32, error) {
+	v := strings.TrimSpace(voice)
+	if v == "" {
+		return nil, nil
+	}
+	if _, err := os.Stat(v); err != nil {
+		return nil, nil
+	}
+	return readWAVAsFloat(v)
+}
+
+// refAudioFor resolves the cloning reference for a request: the per-request
+// Voice takes precedence, falling back to the model-config audio_path. Empty
+// result means no cloning (voice design via Instructions still applies).
+func (o *OmnivoiceCpp) refAudioFor(req *pb.TTSRequest) ([]float32, error) {
+	voice := strings.TrimSpace(req.Voice)
+	if voice == "" {
+		voice = o.audioPath
+	}
+	return o.refAudio(voice)
+}
+
+func reqParam(req *pb.TTSRequest, key string) string {
+	if req.Params == nil {
+		return ""
+	}
+	return req.Params[key]
+}
+
+func (o *OmnivoiceCpp) seedFor(req *pb.TTSRequest) int64 {
+	if s := reqParam(req, "seed"); s != "" {
+		var n int64
+		if _, err := fmt.Sscan(s, &n); err == nil {
+			return n
+		}
+	}
+	return o.opts.seed
+}
+
+func optStr(p *string) string {
+	if p == nil {
+		return ""
+	}
+	return *p
+}
+
+func (o *OmnivoiceCpp) TTS(req *pb.TTSRequest) error {
+	if req.Dst == "" {
+		return fmt.Errorf("omnivoice: TTS requires a destination path")
+	}
+	lang := normalizeLanguage(optStr(req.Language))
+	instruct := optStr(req.Instructions)
+	refText := reqParam(req, "ref_text")
+	seed := o.seedFor(req)
+
+	ref, err := o.refAudioFor(req)
+	if err != nil {
+		return err
+	}
+	var refPtr unsafe.Pointer
+	if len(ref) > 0 {
+		refPtr = unsafe.Pointer(&ref[0])
+	}
+
+	var n int32
+	ptr := CppTTS(req.Text, lang, instruct, refPtr, len(ref), refText, seed,
+		boolToInt(o.opts.denoise), unsafe.Pointer(&n))
+	runtimeKeepAlive(ref)
+	if ptr == 0 || n <= 0 {
+		return fmt.Errorf("omnivoice: synthesis failed")
+	}
+	defer CppPCMFree(ptr)
+	src := unsafe.Slice((*float32)(unsafe.Pointer(ptr)), int(n)) //nolint:govet // C-allocated PCM, copied out before free
+	out := make([]float32, int(n))
+	copy(out, src)
+	return writeWAV24k(req.Dst, out)
+}
+
+// streamState carries the active TTSStream channel to the single shared C
+// callback. base.SingleThread serializes TTS/TTSStream, so one global slot is
+// safe and avoids leaking a purego callback per request (purego callbacks
+// cannot be freed and are capped).
+var (
+	streamMu     sync.Mutex
+	streamChan   chan []byte
+	streamCbOnce sync.Once
+	streamCbPtr  uintptr
+)
+
+// streamCallback is registered once and forwards each PCM chunk to streamChan.
+func streamCallback(samples *float32, nSamples int32, _ uintptr) uintptr {
+	if nSamples <= 0 || samples == nil || streamChan == nil {
+		return 1 // continue
+	}
+	src := unsafe.Slice(samples, int(nSamples))
+	cp := make([]float32, int(nSamples)) // copy out of C memory before returning
+	copy(cp, src)
+	streamChan <- floatToPCM16LE(cp)
+	return 1 // continue
+}
+
+func (o *OmnivoiceCpp) TTSStream(req *pb.TTSRequest, results chan []byte) error {
+	defer close(results)
+	if req.Text == "" {
+		return fmt.Errorf("omnivoice: TTSStream requires text")
+	}
+
+	streamCbOnce.Do(func() {
+		streamCbPtr = purego.NewCallback(streamCallback)
+	})
+
+	lang := normalizeLanguage(optStr(req.Language))
+	instruct := optStr(req.Instructions)
+	refText := reqParam(req, "ref_text")
+	seed := o.seedFor(req)
+
+	ref, err := o.refAudioFor(req)
+	if err != nil {
+		return err
+	}
+	var refPtr unsafe.Pointer
+	if len(ref) > 0 {
+		refPtr = unsafe.Pointer(&ref[0])
+	}
+
+	// Emit the WAV header first so the HTTP layer gets a self-describing stream.
+	results <- wavHeader24k()
+
+	streamMu.Lock()
+	streamChan = results
+	rc := CppTTSStream(req.Text, lang, instruct, refPtr, len(ref), refText, seed,
+		boolToInt(o.opts.denoise), streamCbPtr, 0)
+	streamChan = nil
+	streamMu.Unlock()
+	runtimeKeepAlive(ref)
+
+	if rc != 0 {
+		return fmt.Errorf("omnivoice: streaming synthesis failed (rc=%d)", rc)
+	}
+	return nil
+}

backend/go/omnivoice-cpp/gomnivoicecpp_test.go

@@ -0,0 +1,90 @@
+package main
+
+import (
+	"bytes"
+	"encoding/binary"
+	"testing"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+func TestOmnivoiceCpp(t *testing.T) {
+	RegisterFailHandler(Fail)
+	RunSpecs(t, "omnivoice-cpp suite")
+}
+
+var _ = Describe("normalizeLanguage", func() {
+	DescribeTable("maps caller language to OmniVoice codes",
+		func(in, want string) {
+			Expect(normalizeLanguage(in)).To(Equal(want))
+		},
+		Entry("empty stays empty", "", ""),
+		Entry("english full name", "English", "en"),
+		Entry("chinese full name", "Chinese", "zh"),
+		Entry("locale suffix stripped", "en-US", "en"),
+		Entry("underscore locale", "zh_CN", "zh"),
+		Entry("already a code", "en", "en"),
+		Entry("unknown passes through normalized", "xx", "xx"),
+	)
+})
+
+var _ = Describe("parseOptions", func() {
+	It("extracts codec, use_fa, clamp_fp16, seed, denoise", func() {
+		o := parseOptions([]string{
+			"tokenizer:tok.gguf",
+			"use_fa:true",
+			"clamp_fp16:true",
+			"seed:7",
+			"denoise:false",
+			"unknown:ignored",
+		})
+		Expect(o.codecPath).To(Equal("tok.gguf"))
+		Expect(o.useFA).To(BeTrue())
+		Expect(o.clampFP16).To(BeTrue())
+		Expect(o.seed).To(Equal(int64(7)))
+		Expect(o.denoise).To(BeFalse())
+	})
+
+	It("accepts codec: as an alias for tokenizer:", func() {
+		o := parseOptions([]string{"codec:c.gguf"})
+		Expect(o.codecPath).To(Equal("c.gguf"))
+	})
+
+	It("defaults seed to -1 and denoise to true", func() {
+		o := parseOptions(nil)
+		Expect(o.seed).To(Equal(int64(-1)))
+		Expect(o.denoise).To(BeTrue())
+	})
+})
+
+var _ = Describe("wavHeader24k", func() {
+	It("emits a 44-byte streaming WAV header at 24 kHz mono 16-bit", func() {
+		h := wavHeader24k()
+		Expect(h).To(HaveLen(44))
+		Expect(string(h[0:4])).To(Equal("RIFF"))
+		Expect(string(h[8:12])).To(Equal("WAVE"))
+		Expect(string(h[12:16])).To(Equal("fmt "))
+		Expect(string(h[36:40])).To(Equal("data"))
+		var sampleRate uint32
+		Expect(binary.Read(bytes.NewReader(h[24:28]), binary.LittleEndian, &sampleRate)).To(Succeed())
+		Expect(sampleRate).To(Equal(uint32(24000)))
+	})
+})
+
+var _ = Describe("floatToPCM16LE", func() {
+	It("clamps and converts float PCM to little-endian int16 bytes", func() {
+		b := floatToPCM16LE([]float32{0, 1.0, -1.0, 2.0, -2.0})
+		Expect(b).To(HaveLen(10)) // 5 samples * 2 bytes
+		read := func(off int) int16 {
+			var v int16
+			_ = binary.Read(bytes.NewReader(b[off:off+2]), binary.LittleEndian, &v)
+			return v
+		}
+		Expect(read(0)).To(Equal(int16(0)))
+		Expect(read(2)).To(Equal(int16(32767)))
+		Expect(read(4)).To(Equal(int16(-32767)))
+		Expect(read(6)).To(Equal(int16(32767)))  // clamped from 2.0
+		Expect(read(8)).To(Equal(int16(-32767))) // clamped from -2.0
+	})
+})

backend/go/omnivoice-cpp/main.go

@@ -0,0 +1,48 @@
+package main
+
+// Note: this is started internally by LocalAI and a server is allocated for each model
+import (
+	"flag"
+	"os"
+
+	"github.com/ebitengine/purego"
+	grpc "github.com/mudler/LocalAI/pkg/grpc"
+)
+
+var (
+	addr = flag.String("addr", "localhost:50051", "the address to connect to")
+)
+
+type LibFuncs struct {
+	FuncPtr any
+	Name    string
+}
+
+func main() {
+	libName := os.Getenv("OMNIVOICE_LIBRARY")
+	if libName == "" {
+		libName = "./libgomnivoicecpp-fallback.so"
+	}
+
+	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
+	if err != nil {
+		panic(err)
+	}
+
+	libFuncs := []LibFuncs{
+		{&CppLoad, "omni_load"},
+		{&CppTTS, "omni_tts"},
+		{&CppTTSStream, "omni_tts_stream"},
+		{&CppPCMFree, "omni_pcm_free"},
+		{&CppUnload, "omni_unload"},
+	}
+	for _, lf := range libFuncs {
+		purego.RegisterLibFunc(lf.FuncPtr, lib, lf.Name)
+	}
+
+	flag.Parse()
+
+	if err := grpc.StartServer(*addr, &OmnivoiceCpp{}); err != nil {
+		panic(err)
+	}
+}

backend/go/omnivoice-cpp/options.go

@@ -0,0 +1,74 @@
+package main
+
+import (
+	"strconv"
+	"strings"
+)
+
+// loadOptions holds the parsed model-level options for OmniVoice.
+type loadOptions struct {
+	codecPath string
+	useFA     bool
+	clampFP16 bool
+	seed      int64
+	denoise   bool
+}
+
+func splitOption(o string) (key, value string, ok bool) {
+	i := strings.Index(o, ":")
+	if i < 0 {
+		return "", "", false
+	}
+	return strings.TrimSpace(o[:i]), strings.TrimSpace(o[i+1:]), true
+}
+
+// parseOptions reads the backend "key:value" option slice. Unknown keys are
+// ignored. Defaults: seed -1 (engine default), denoise true.
+func parseOptions(opts []string) loadOptions {
+	o := loadOptions{seed: -1, denoise: true}
+	for _, oo := range opts {
+		key, value, ok := splitOption(oo)
+		if !ok {
+			continue
+		}
+		switch key {
+		case "tokenizer", "codec":
+			o.codecPath = value
+		case "use_fa":
+			o.useFA = value == "true" || value == "1"
+		case "clamp_fp16":
+			o.clampFP16 = value == "true" || value == "1"
+		case "seed":
+			if n, err := strconv.ParseInt(value, 10, 64); err == nil {
+				o.seed = n
+			}
+		case "denoise":
+			o.denoise = value == "true" || value == "1"
+		}
+	}
+	return o
+}
+
+// languageNameAliases maps full language names to OmniVoice codes. OmniVoice's
+// lang hint accepts "" (auto), "en", "zh" per the upstream convention; other
+// codes pass through and the engine treats unknown hints as auto.
+var languageNameAliases = map[string]string{
+	"english": "en",
+	"chinese": "zh",
+}
+
+// normalizeLanguage lowercases, trims, strips a region/locale suffix, and
+// resolves common full names. Empty stays empty so the engine auto-detects.
+func normalizeLanguage(lang string) string {
+	lang = strings.ToLower(strings.TrimSpace(lang))
+	if lang == "" {
+		return ""
+	}
+	if i := strings.IndexAny(lang, "-_."); i >= 0 {
+		lang = lang[:i]
+	}
+	if code, ok := languageNameAliases[lang]; ok {
+		return code
+	}
+	return lang
+}

backend/go/omnivoice-cpp/package.sh

@@ -0,0 +1,64 @@
+#!/bin/bash
+
+# Script to copy the appropriate libraries based on architecture
+# This script is used in the final stage of the Dockerfile
+
+set -e
+
+CURDIR=$(dirname "$(realpath $0)")
+REPO_ROOT="${CURDIR}/../../.."
+
+# Create lib directory
+mkdir -p $CURDIR/package/lib
+
+cp -avf $CURDIR/omnivoice-cpp $CURDIR/package/
+cp -fv $CURDIR/libgomnivoicecpp-*.so $CURDIR/package/
+cp -fv $CURDIR/run.sh $CURDIR/package/
+
+# Detect architecture and copy appropriate libraries
+if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
+    # x86_64 architecture
+    echo "Detected x86_64 architecture, copying x86_64 libraries..."
+    cp -arfLv /lib64/ld-linux-x86-64.so.2 $CURDIR/package/lib/ld.so
+    cp -arfLv /lib/x86_64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
+    cp -arfLv /lib/x86_64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
+elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
+    # ARM64 architecture
+    echo "Detected ARM64 architecture, copying ARM64 libraries..."
+    cp -arfLv /lib/ld-linux-aarch64.so.1 $CURDIR/package/lib/ld.so
+    cp -arfLv /lib/aarch64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
+    cp -arfLv /lib/aarch64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
+elif [ $(uname -s) = "Darwin" ]; then
+    echo "Detected Darwin"
+else
+    echo "Error: Could not detect architecture"
+    exit 1
+fi
+
+# Package GPU libraries based on BUILD_TYPE
+GPU_LIB_SCRIPT="${REPO_ROOT}/scripts/build/package-gpu-libs.sh"
+if [ -f "$GPU_LIB_SCRIPT" ]; then
+    echo "Packaging GPU libraries for BUILD_TYPE=${BUILD_TYPE:-cpu}..."
+    source "$GPU_LIB_SCRIPT" "$CURDIR/package/lib"
+    package_gpu_libs
+fi
+
+echo "Packaging completed successfully"
+ls -liah $CURDIR/package/
+ls -liah $CURDIR/package/lib/

backend/go/omnivoice-cpp/run.sh

@@ -0,0 +1,52 @@
+#!/bin/bash
+set -ex
+
+# Get the absolute current dir where the script is located
+CURDIR=$(dirname "$(realpath $0)")
+
+cd /
+
+echo "CPU info:"
+if [ "$(uname)" != "Darwin" ]; then
+	grep -e "model\sname" /proc/cpuinfo | head -1
+	grep -e "flags" /proc/cpuinfo | head -1
+fi
+
+LIBRARY="$CURDIR/libgomnivoicecpp-fallback.so"
+
+if [ "$(uname)" != "Darwin" ]; then
+	if grep -q -e "\savx\s" /proc/cpuinfo ; then
+		echo "CPU:    AVX    found OK"
+		if [ -e $CURDIR/libgomnivoicecpp-avx.so ]; then
+			LIBRARY="$CURDIR/libgomnivoicecpp-avx.so"
+		fi
+	fi
+
+	if grep -q -e "\savx2\s" /proc/cpuinfo ; then
+		echo "CPU:    AVX2   found OK"
+		if [ -e $CURDIR/libgomnivoicecpp-avx2.so ]; then
+			LIBRARY="$CURDIR/libgomnivoicecpp-avx2.so"
+		fi
+	fi
+
+	# Check avx 512
+	if grep -q -e "\savx512f\s" /proc/cpuinfo ; then
+		echo "CPU:    AVX512F found OK"
+		if [ -e $CURDIR/libgomnivoicecpp-avx512.so ]; then
+			LIBRARY="$CURDIR/libgomnivoicecpp-avx512.so"
+		fi
+	fi
+fi
+
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
+export OMNIVOICE_LIBRARY=$LIBRARY
+
+# If there is a lib/ld.so, use it
+if [ -f $CURDIR/lib/ld.so ]; then
+	echo "Using lib/ld.so"
+	echo "Using library: $LIBRARY"
+	exec $CURDIR/lib/ld.so $CURDIR/omnivoice-cpp "$@"
+fi
+
+echo "Using library: $LIBRARY"
+exec $CURDIR/omnivoice-cpp "$@"

backend/go/omnivoice-cpp/test.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+set -e
+
+CURDIR=$(dirname "$(realpath $0)")
+cd "$CURDIR"
+
+echo "Running omnivoice-cpp backend tests..."
+
+if [ -z "$OMNIVOICE_MODEL" ]; then
+    MODEL_DIR="./omnivoice-models"
+    mkdir -p "$MODEL_DIR"
+    REPO_ID="Serveurperso/OmniVoice-GGUF"
+    BASE_URL="https://huggingface.co/${REPO_ID}/resolve/main"
+    FILES=( "omnivoice-base-Q4_K_M.gguf" "omnivoice-tokenizer-Q4_K_M.gguf" )
+    for file in "${FILES[@]}"; do
+        dest="${MODEL_DIR}/${file}"
+        if [ -f "${dest}" ]; then
+            echo "  [skip] ${file}"
+        else
+            echo "  [download] ${file}..."
+            curl -L -o "${dest}" "${BASE_URL}/${file}" --progress-bar
+        fi
+    done
+    export OMNIVOICE_MODEL="${MODEL_DIR}/omnivoice-base-Q4_K_M.gguf"
+    export OMNIVOICE_CODEC="${MODEL_DIR}/omnivoice-tokenizer-Q4_K_M.gguf"
+fi
+
+go test -v -timeout 1200s .
+
+echo "All omnivoice-cpp e2e tests passed."

backend/go/parakeet-cpp/Makefile

@@ -1,6 +1,6 @@
 # parakeet-cpp backend Makefile.
 #
-# Upstream pin lives below as PARAKEET_VERSION?=b8012f11e5269126eddb7f4fd02f891a2ccc29b0
+# Upstream pin lives below as PARAKEET_VERSION?=92a5f0306be354c109150fe58ae4cc4f8a21ca45
 # (.github/bump_deps.sh) can find and update it - matches the
 # whisper.cpp / ds4 / vibevoice-cpp convention.
 #
@@ -15,7 +15,7 @@
 # That's what the L0 smoke test uses. The default target below does the
 # proper clone-at-pin + cmake build so CI doesn't need a side-checkout.
 
-PARAKEET_VERSION?=b8012f11e5269126eddb7f4fd02f891a2ccc29b0
+PARAKEET_VERSION?=92a5f0306be354c109150fe58ae4cc4f8a21ca45
 PARAKEET_REPO?=https://github.com/mudler/parakeet.cpp
 
 GOCMD?=go

backend/go/qwen3-tts-cpp/CMakeLists.txt

@@ -3,35 +3,36 @@ project(goqwen3ttscpp LANGUAGES C CXX)
 set(CMAKE_POSITION_INDEPENDENT_CODE ON)
 set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
 
-set(QWEN3TTS_DIR ${CMAKE_CURRENT_SOURCE_DIR}/sources/qwen3-tts.cpp)
+set(QWENTTS_DIR ${CMAKE_CURRENT_SOURCE_DIR}/sources/qwentts.cpp)
 
 # Override upstream's CMAKE_CUDA_ARCHITECTURES before add_subdirectory.
 if(NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
     set(CMAKE_CUDA_ARCHITECTURES "75-virtual;80-virtual;86-real;89-real")
 endif()
 
-# Build ggml from the upstream's submodule FIRST, so that ggml/ggml-base/ggml-cpu
-# CMake targets exist when the upstream project references them by name.
-# The upstream CMakeLists.txt uses target_link_libraries(... ggml ggml-base ggml-cpu)
-# with target_link_directories pointing at a pre-built ggml/build/. By adding ggml
-# as a subdirectory here, CMake resolves those names as targets instead.
-add_subdirectory(${QWEN3TTS_DIR}/ggml ggml EXCLUDE_FROM_ALL)
+# Add the upstream project. Its own CMakeLists adds ggml + cpp-httplib + yyjson
+# and builds qwen-core (STATIC, the qt_* impl). EXCLUDE_FROM_ALL keeps its CLI
+# tools / tts-server / tests from building unless referenced.
+add_subdirectory(${QWENTTS_DIR} qwentts EXCLUDE_FROM_ALL)
 
-# Now add the upstream project
-add_subdirectory(${QWEN3TTS_DIR} qwen3tts EXCLUDE_FROM_ALL)
+# Upstream generates version.h into its own CMAKE_CURRENT_BINARY_DIR and adds
+# the top-level ${CMAKE_BINARY_DIR} to qwen-core's include path. Under
+# add_subdirectory those two dirs differ (<build>/qwentts vs <build>), so
+# qwen.cpp cannot find version.h. Point qwen-core at the subproject binary dir
+# where version.h is actually generated. (Fix lives here, never in the fetched
+# upstream checkout.)
+target_include_directories(qwen-core PRIVATE ${CMAKE_BINARY_DIR}/qwentts)
 
 add_library(goqwen3ttscpp MODULE cpp/goqwen3ttscpp.cpp)
-target_link_libraries(goqwen3ttscpp PRIVATE qwen3_tts)
+target_link_libraries(goqwen3ttscpp PRIVATE qwen-core)
 
-target_include_directories(goqwen3ttscpp PRIVATE ${QWEN3TTS_DIR}/src)
-target_include_directories(goqwen3ttscpp SYSTEM PRIVATE ${QWEN3TTS_DIR}/ggml/include)
+target_include_directories(goqwen3ttscpp PRIVATE ${QWENTTS_DIR}/src)
+target_include_directories(goqwen3ttscpp SYSTEM PRIVATE ${QWENTTS_DIR}/ggml/include)
 
-# Link GPU backends if available
-foreach(backend blas cuda metal vulkan)
+# Link GPU backends if the upstream ggml created them.
+foreach(backend blas cuda metal vulkan sycl)
     if(TARGET ggml-${backend})
         target_link_libraries(goqwen3ttscpp PRIVATE ggml-${backend})
-        string(TOUPPER ${backend} BACKEND_UPPER)
-        target_compile_definitions(goqwen3ttscpp PRIVATE QWEN3TTS_HAVE_${BACKEND_UPPER})
         if(backend STREQUAL "cuda")
             find_package(CUDAToolkit QUIET)
             if(CUDAToolkit_FOUND)
@@ -44,12 +45,8 @@ endforeach()
 if(MSVC)
     target_compile_options(goqwen3ttscpp PRIVATE /W4 /wd4100 /wd4505)
 else()
-    target_compile_options(goqwen3ttscpp PRIVATE -Wall -Wextra -Wshadow -Wconversion
-                          -Wno-unused-parameter -Wno-unused-function -Wno-sign-conversion)
-endif()
-
-if(CMAKE_CXX_COMPILER_ID MATCHES "GNU" AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS 9.0)
-    target_link_libraries(goqwen3ttscpp PRIVATE stdc++fs)
+    target_compile_options(goqwen3ttscpp PRIVATE -Wall -Wextra
+                          -Wno-unused-parameter -Wno-unused-function)
 endif()
 
 set_property(TARGET goqwen3ttscpp PROPERTY CXX_STANDARD 17)

backend/go/qwen3-tts-cpp/Makefile

@@ -6,9 +6,9 @@ GOCMD?=go
 GO_TAGS?=
 JOBS?=$(shell nproc --ignore=1)
 
-# qwen3-tts.cpp version
-QWEN3TTS_REPO?=https://github.com/predict-woo/qwen3-tts.cpp
-QWEN3TTS_CPP_VERSION?=136e5d36c17083da0321fd96512dc7b263f94a44
+# qwentts.cpp version
+QWEN3TTS_REPO?=https://github.com/ServeurpersoCom/qwentts.cpp
+QWEN3TTS_CPP_VERSION?=0bf4a18b22e8bb8718d95294e9f7f45c0d4270a4
 SO_TARGET?=libgoqwen3ttscpp.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
@@ -49,9 +49,9 @@ ifeq ($(BUILD_TYPE),sycl_f32)
 		-DCMAKE_CXX_COMPILER=icpx
 endif
 
-sources/qwen3-tts.cpp:
-	mkdir -p sources/qwen3-tts.cpp
-	cd sources/qwen3-tts.cpp && \
+sources/qwentts.cpp:
+	mkdir -p sources/qwentts.cpp
+	cd sources/qwentts.cpp && \
 	git init && \
 	git remote add origin $(QWEN3TTS_REPO) && \
 	git fetch origin && \
@@ -78,7 +78,7 @@ package: qwen3-tts-cpp
 build: package
 
 clean: purge
-	rm -rf libgoqwen3ttscpp*.so package sources/qwen3-tts.cpp qwen3-tts-cpp
+	rm -rf libgoqwen3ttscpp*.so package sources/qwentts.cpp qwen3-tts-cpp
 
 purge:
 	rm -rf build*
@@ -88,24 +88,24 @@ purge:
 
 # Build all variants (Linux only)
 ifeq ($(UNAME_S),Linux)
-libgoqwen3ttscpp-avx.so: sources/qwen3-tts.cpp
+libgoqwen3ttscpp-avx.so: sources/qwentts.cpp
 	$(info ${GREEN}I qwen3-tts-cpp build info:avx${RESET})
 	SO_TARGET=libgoqwen3ttscpp-avx.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgoqwen3ttscpp-custom
 	rm -rf build-libgoqwen3ttscpp-avx.so
 
-libgoqwen3ttscpp-avx2.so: sources/qwen3-tts.cpp
+libgoqwen3ttscpp-avx2.so: sources/qwentts.cpp
 	$(info ${GREEN}I qwen3-tts-cpp build info:avx2${RESET})
 	SO_TARGET=libgoqwen3ttscpp-avx2.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) libgoqwen3ttscpp-custom
 	rm -rf build-libgoqwen3ttscpp-avx2.so
 
-libgoqwen3ttscpp-avx512.so: sources/qwen3-tts.cpp
+libgoqwen3ttscpp-avx512.so: sources/qwentts.cpp
 	$(info ${GREEN}I qwen3-tts-cpp build info:avx512${RESET})
 	SO_TARGET=libgoqwen3ttscpp-avx512.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=on -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) libgoqwen3ttscpp-custom
 	rm -rf build-libgoqwen3ttscpp-avx512.so
 endif
 
 # Build fallback variant (all platforms)
-libgoqwen3ttscpp-fallback.so: sources/qwen3-tts.cpp
+libgoqwen3ttscpp-fallback.so: sources/qwentts.cpp
 	$(info ${GREEN}I qwen3-tts-cpp build info:fallback${RESET})
 	SO_TARGET=libgoqwen3ttscpp-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgoqwen3ttscpp-custom
 	rm -rf build-libgoqwen3ttscpp-fallback.so

backend/go/qwen3-tts-cpp/audio.go

@@ -0,0 +1,128 @@
+package main
+
+import (
+	"bytes"
+	"encoding/binary"
+	"fmt"
+	"os"
+	"runtime"
+
+	"github.com/go-audio/audio"
+	"github.com/go-audio/wav"
+)
+
+const qwen3ttsSampleRate = 24000
+
+// wavHeader24k returns a 44-byte WAV header for a streaming 24 kHz mono 16-bit
+// PCM stream, with placeholder (0xFFFFFFFF) sizes since the total length is
+// unknown up front. Emitted as the first chunk of TTSStream so the HTTP layer
+// receives a self-describing WAV (the gRPC TTSStream path never sets Message,
+// so the backend owns the header - see core/backend/tts.go:ModelTTSStream).
+func wavHeader24k() []byte {
+	var buf bytes.Buffer
+	w := func(v any) { _ = binary.Write(&buf, binary.LittleEndian, v) }
+	buf.WriteString("RIFF")
+	w(uint32(0xFFFFFFFF))
+	buf.WriteString("WAVE")
+	buf.WriteString("fmt ")
+	w(uint32(16))                     // Subchunk1Size
+	w(uint16(1))                      // PCM
+	w(uint16(1))                      // mono
+	w(uint32(qwen3ttsSampleRate))     // sample rate
+	w(uint32(qwen3ttsSampleRate * 2)) // byte rate = SR * blockAlign
+	w(uint16(2))                      // block align (16-bit mono)
+	w(uint16(16))                     // bits per sample
+	buf.WriteString("data")
+	w(uint32(0xFFFFFFFF))
+	return buf.Bytes()
+}
+
+// floatToPCM16LE clamps each sample to [-1,1] and encodes it as little-endian
+// signed 16-bit PCM.
+func floatToPCM16LE(samples []float32) []byte {
+	out := make([]byte, len(samples)*2)
+	for i, s := range samples {
+		if s > 1 {
+			s = 1
+		} else if s < -1 {
+			s = -1
+		}
+		v := int16(s * 32767)
+		out[i*2] = byte(v)
+		out[i*2+1] = byte(v >> 8)
+	}
+	return out
+}
+
+// writeWAV24k writes samples as a finalized 24 kHz mono 16-bit WAV at dst.
+func writeWAV24k(dst string, samples []float32) error {
+	f, err := os.Create(dst)
+	if err != nil {
+		return fmt.Errorf("qwen3-tts: create %q: %w", dst, err)
+	}
+	enc := wav.NewEncoder(f, qwen3ttsSampleRate, 16, 1, 1)
+	ints := make([]int, len(samples))
+	for i, s := range samples {
+		if s > 1 {
+			s = 1
+		} else if s < -1 {
+			s = -1
+		}
+		ints[i] = int(s * 32767)
+	}
+	b := &audio.IntBuffer{
+		Format:         &audio.Format{NumChannels: 1, SampleRate: qwen3ttsSampleRate},
+		Data:           ints,
+		SourceBitDepth: 16,
+	}
+	if err := enc.Write(b); err != nil {
+		_ = enc.Close()
+		_ = f.Close()
+		return fmt.Errorf("qwen3-tts: encode WAV: %w", err)
+	}
+	if err := enc.Close(); err != nil {
+		_ = f.Close()
+		return fmt.Errorf("qwen3-tts: finalize WAV: %w", err)
+	}
+	return f.Close()
+}
+
+// readWAVAsFloat decodes a WAV file (any sample rate/channels) to a mono
+// float32 slice in [-1,1] for use as cloning reference audio. qwentts expects
+// 24 kHz; callers should supply 24 kHz reference clips.
+func readWAVAsFloat(path string) ([]float32, error) {
+	f, err := os.Open(path)
+	if err != nil {
+		return nil, fmt.Errorf("qwen3-tts: open ref %q: %w", path, err)
+	}
+	defer func() { _ = f.Close() }()
+
+	dec := wav.NewDecoder(f)
+	buf, err := dec.FullPCMBuffer()
+	if err != nil {
+		return nil, fmt.Errorf("qwen3-tts: decode ref %q: %w", path, err)
+	}
+	ch := int(buf.Format.NumChannels)
+	if ch < 1 {
+		ch = 1
+	}
+	bitDepth := int(buf.SourceBitDepth)
+	if bitDepth == 0 {
+		bitDepth = 16
+	}
+	scale := float32(int64(1) << uint(bitDepth-1))
+	n := len(buf.Data) / ch
+	out := make([]float32, n)
+	for i := 0; i < n; i++ {
+		var acc int
+		for c := 0; c < ch; c++ {
+			acc += buf.Data[i*ch+c]
+		}
+		out[i] = float32(acc) / float32(ch) / scale
+	}
+	return out, nil
+}
+
+// runtimeKeepAlive prevents the GC from reclaiming the reference-audio slice
+// while its backing pointer is in use across the C call.
+func runtimeKeepAlive(v any) { runtime.KeepAlive(v) }

backend/go/qwen3-tts-cpp/audiopath_test.go

@@ -0,0 +1,54 @@
+package main
+
+import (
+	"path/filepath"
+
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+// These specs pin the voice-selection logic in resolveRequest, in particular
+// the config-level audio_path (tts.audio_path -> ModelOptions.AudioPath) being
+// used as the default voice-cloning reference. No model/C library is needed:
+// resolveRequest only reads the reference WAV via readWAVAsFloat (pure Go).
+var _ = Describe("resolveRequest voice/clone selection", func() {
+	var dir, refWav string
+
+	BeforeEach(func() {
+		dir = GinkgoT().TempDir()
+		refWav = filepath.Join(dir, "ref.wav")
+		// 0.5s of non-silent 24kHz mono audio as a clone reference.
+		samples := make([]float32, qwen3ttsSampleRate/2)
+		for i := range samples {
+			samples[i] = 0.1
+		}
+		Expect(writeWAV24k(refWav, samples)).To(Succeed())
+	})
+
+	It("uses the config audio_path as the clone reference when Voice is empty", func() {
+		q := &Qwen3TtsCpp{audioPath: refWav}
+		_, _, speaker, _, ref, _, err := q.resolveRequest(&pb.TTSRequest{Text: "hi"})
+		Expect(err).ToNot(HaveOccurred())
+		Expect(speaker).To(BeEmpty())
+		Expect(len(ref)).To(Equal(qwen3ttsSampleRate / 2))
+	})
+
+	It("lets a per-request audio Voice override audio_path", func() {
+		other := filepath.Join(dir, "other.wav")
+		Expect(writeWAV24k(other, make([]float32, 100))).To(Succeed())
+		q := &Qwen3TtsCpp{audioPath: refWav}
+		_, _, speaker, _, ref, _, err := q.resolveRequest(&pb.TTSRequest{Text: "hi", Voice: other})
+		Expect(err).ToNot(HaveOccurred())
+		Expect(speaker).To(BeEmpty())
+		Expect(len(ref)).To(Equal(100))
+	})
+
+	It("does not trigger audio_path cloning for a named-speaker Voice", func() {
+		q := &Qwen3TtsCpp{audioPath: refWav}
+		_, _, speaker, _, ref, _, err := q.resolveRequest(&pb.TTSRequest{Text: "hi", Voice: "serena"})
+		Expect(err).ToNot(HaveOccurred())
+		Expect(speaker).To(Equal("serena"))
+		Expect(ref).To(BeNil())
+	})
+})

backend/go/qwen3-tts-cpp/cpp/goqwen3ttscpp.cpp

@@ -1,161 +1,191 @@
 #include "goqwen3ttscpp.h"
 #include "ggml-backend.h"
-#include "qwen3_tts.h"
+#include "qwen.h"
 
-#include <cmath>
 #include <cstdio>
 #include <cstdlib>
 #include <cstring>
-#include <string>
 
-using namespace qwen3_tts;
+static qt_context *g_ctx = nullptr;
 
-// Global engine (loaded once, reused across requests)
-static Qwen3TTS *g_engine = nullptr;
-static bool g_loaded = false;
-static int g_threads = 4;
-
-static void ggml_log_cb(enum ggml_log_level level, const char *log, void *data) {
-    const char *level_str;
+static void ggml_log_cb(enum ggml_log_level level, const char *log,
+                        void * /*data*/) {
     if (!log)
         return;
+    const char *lvl = "?????";
     switch (level) {
-    case GGML_LOG_LEVEL_DEBUG:
-        level_str = "DEBUG";
-        break;
-    case GGML_LOG_LEVEL_INFO:
-        level_str = "INFO";
-        break;
-    case GGML_LOG_LEVEL_WARN:
-        level_str = "WARN";
-        break;
-    case GGML_LOG_LEVEL_ERROR:
-        level_str = "ERROR";
-        break;
-    default:
-        level_str = "?????";
-        break;
+    case GGML_LOG_LEVEL_DEBUG: lvl = "DEBUG"; break;
+    case GGML_LOG_LEVEL_INFO:  lvl = "INFO";  break;
+    case GGML_LOG_LEVEL_WARN:  lvl = "WARN";  break;
+    case GGML_LOG_LEVEL_ERROR: lvl = "ERROR"; break;
+    default: break;
     }
-    fprintf(stderr, "[%-5s] ", level_str);
-    fputs(log, stderr);
+    fprintf(stderr, "[%-5s] %s", lvl, log);
     fflush(stderr);
 }
 
-// Map language string to language_id token used by the model
-static int language_to_id(const char *lang) {
-    if (!lang || lang[0] == '\0')
-        return 2050; // default: English
-    std::string l(lang);
-    if (l == "en")
-        return 2050;
-    if (l == "ru")
-        return 2069;
-    if (l == "zh")
-        return 2055;
-    if (l == "ja")
-        return 2058;
-    if (l == "ko")
-        return 2064;
-    if (l == "de")
-        return 2053;
-    if (l == "fr")
-        return 2061;
-    if (l == "es")
-        return 2054;
-    if (l == "it")
-        return 2056;
-    if (l == "pt")
-        return 2057;
-    fprintf(stderr, "[qwen3-tts-cpp] Unknown language '%s', defaulting to English\n",
-            lang);
-    return 2050;
-}
-
-int load_model(const char *model_dir, int n_threads) {
+int qt3_load(const char *talker_path, const char *codec_path, int use_fa,
+             int clamp_fp16) {
     ggml_log_set(ggml_log_cb, nullptr);
     ggml_backend_load_all();
 
-    if (n_threads <= 0)
-        n_threads = 4;
-    g_threads = n_threads;
-
-    fprintf(stderr, "[qwen3-tts-cpp] Loading models from %s (threads=%d)\n",
-            model_dir, n_threads);
-
-    g_engine = new Qwen3TTS();
-    if (!g_engine->load_models(model_dir)) {
-        fprintf(stderr, "[qwen3-tts-cpp] FATAL: failed to load models from %s\n",
-                model_dir);
-        delete g_engine;
-        g_engine = nullptr;
+    if (!talker_path || talker_path[0] == '\0') {
+        fprintf(stderr, "[qwen3-tts-cpp] ERROR: talker_path is required\n");
         return 1;
     }
-
-    g_loaded = true;
-    fprintf(stderr, "[qwen3-tts-cpp] Models loaded successfully\n");
-    return 0;
-}
-
-int synthesize(const char *text, const char *ref_audio_path, const char *dst,
-               const char *language, float temperature, float top_p,
-               int top_k, float repetition_penalty, int max_audio_tokens,
-               int n_threads) {
-    if (!g_loaded || !g_engine) {
-        fprintf(stderr, "[qwen3-tts-cpp] ERROR: models not loaded\n");
-        return 1;
-    }
-
-    if (!text || !dst) {
-        fprintf(stderr, "[qwen3-tts-cpp] ERROR: text and dst are required\n");
+    if (!codec_path || codec_path[0] == '\0') {
+        fprintf(stderr, "[qwen3-tts-cpp] ERROR: codec_path is required\n");
         return 2;
     }
 
-    tts_params params;
-    params.max_audio_tokens = max_audio_tokens > 0 ? max_audio_tokens : 4096;
-    params.temperature = temperature;
-    params.top_p = top_p;
-    params.top_k = top_k;
-    params.repetition_penalty = repetition_penalty;
-    params.n_threads = n_threads > 0 ? n_threads : g_threads;
-    params.language_id = language_to_id(language);
+    qt_init_params p;
+    qt_init_default_params(&p);
+    p.talker_path = talker_path;
+    p.codec_path = codec_path;
+    p.use_fa = use_fa != 0;
+    p.clamp_fp16 = clamp_fp16 != 0;
 
-    fprintf(stderr, "[qwen3-tts-cpp] Synthesizing: text='%.50s%s', lang_id=%d, "
-                    "temp=%.2f, threads=%d\n",
-            text, (strlen(text) > 50 ? "..." : ""), params.language_id,
-            temperature, params.n_threads);
+    fprintf(stderr, "[qwen3-tts-cpp] Loading talker=%s codec=%s\n", talker_path,
+            codec_path);
 
-    tts_result result;
-    bool has_ref = ref_audio_path && ref_audio_path[0] != '\0';
-
-    if (has_ref) {
-        fprintf(stderr, "[qwen3-tts-cpp] Voice cloning with ref: %s\n",
-                ref_audio_path);
-        result = g_engine->synthesize_with_voice(text, ref_audio_path, params);
-    } else {
-        result = g_engine->synthesize(text, params);
-    }
-
-    if (!result.success) {
-        fprintf(stderr, "[qwen3-tts-cpp] ERROR: synthesis failed: %s\n",
-                result.error_msg.c_str());
+    g_ctx = qt_init(&p);
+    if (!g_ctx) {
+        fprintf(stderr, "[qwen3-tts-cpp] FATAL: qt_init failed: %s\n",
+                qt_last_error());
         return 3;
     }
-
-    int n_samples = (int)result.audio.size();
-    if (n_samples == 0) {
-        fprintf(stderr, "[qwen3-tts-cpp] ERROR: synthesis produced no samples\n");
-        return 4;
-    }
-
-    fprintf(stderr,
-            "[qwen3-tts-cpp] Synthesis done: %d samples (%.2fs @ 24kHz)\n",
-            n_samples, (float)n_samples / 24000.0f);
-
-    if (!save_audio_file(dst, result.audio, result.sample_rate)) {
-        fprintf(stderr, "[qwen3-tts-cpp] ERROR: failed to write %s\n", dst);
-        return 5;
-    }
-
-    fprintf(stderr, "[qwen3-tts-cpp] Wrote %s\n", dst);
+    fprintf(stderr, "[qwen3-tts-cpp] Model loaded (%s)\n", qt_version());
     return 0;
 }
+
+// Fill a qt_tts_params from the flat wrapper arguments. Unset/zero scalars keep
+// the qt defaults (temperature 0.9, top_k 50, top_p 1.0, rep 1.05, max 2048).
+static void fill_params(qt_tts_params *tp, const char *text, const char *lang,
+                        const char *instruct, const char *speaker,
+                        const float *ref_samples, int ref_n,
+                        const char *ref_text, long long seed, float temperature,
+                        int top_k, float top_p, float repetition_penalty,
+                        int max_new_tokens) {
+    qt_tts_default_params(tp);
+    tp->text = text ? text : "";
+    if (lang && lang[0] != '\0')
+        tp->lang = lang; // else keep default NULL -> auto
+    if (instruct && instruct[0] != '\0')
+        tp->instruct = instruct;
+    if (speaker && speaker[0] != '\0')
+        tp->speaker = speaker;
+    if (ref_samples && ref_n > 0) {
+        tp->ref_audio_24k = ref_samples;
+        tp->ref_n_samples = ref_n;
+        if (ref_text && ref_text[0] != '\0')
+            tp->ref_text = ref_text;
+    }
+    if (seed >= 0)
+        tp->seed = (int64_t)seed; // else default -1 (random)
+    if (temperature > 0.0f)
+        tp->temperature = temperature;
+    if (top_k > 0)
+        tp->top_k = top_k;
+    if (top_p > 0.0f)
+        tp->top_p = top_p;
+    if (repetition_penalty > 0.0f)
+        tp->repetition_penalty = repetition_penalty;
+    if (max_new_tokens > 0)
+        tp->max_new_tokens = max_new_tokens;
+}
+
+float *qt3_tts(const char *text, const char *lang, const char *instruct,
+               const char *speaker, const float *ref_samples, int ref_n,
+               const char *ref_text, long long seed, float temperature,
+               int top_k, float top_p, float repetition_penalty,
+               int max_new_tokens, int *out_n) {
+    if (out_n)
+        *out_n = 0;
+    if (!g_ctx) {
+        fprintf(stderr, "[qwen3-tts-cpp] ERROR: model not loaded\n");
+        return nullptr;
+    }
+    if (!text || text[0] == '\0') {
+        fprintf(stderr, "[qwen3-tts-cpp] ERROR: text is required\n");
+        return nullptr;
+    }
+    qt_tts_params tp;
+    fill_params(&tp, text, lang, instruct, speaker, ref_samples, ref_n,
+                ref_text, seed, temperature, top_k, top_p, repetition_penalty,
+                max_new_tokens);
+
+    qt_audio out = {0};
+    enum qt_status rc = qt_synthesize(g_ctx, &tp, &out);
+    if (rc != QT_STATUS_OK || out.n_samples <= 0 || !out.samples) {
+        fprintf(stderr, "[qwen3-tts-cpp] ERROR: synthesize failed (rc=%d): %s\n",
+                (int)rc, qt_last_error());
+        qt_audio_free(&out);
+        return nullptr;
+    }
+
+    // Copy into a plain malloc buffer the Go side frees via qt3_pcm_free.
+    size_t bytes = (size_t)out.n_samples * sizeof(float);
+    float *buf = (float *)malloc(bytes);
+    if (!buf) {
+        fprintf(stderr, "[qwen3-tts-cpp] ERROR: malloc(%zu) failed\n", bytes);
+        qt_audio_free(&out);
+        return nullptr;
+    }
+    memcpy(buf, out.samples, bytes);
+    if (out_n)
+        *out_n = out.n_samples;
+    qt_audio_free(&out);
+    return buf;
+}
+
+int qt3_tts_stream(const char *text, const char *lang, const char *instruct,
+                   const char *speaker, const float *ref_samples, int ref_n,
+                   const char *ref_text, long long seed, float temperature,
+                   int top_k, float top_p, float repetition_penalty,
+                   int max_new_tokens, qt3_chunk_cb cb, void *user_data) {
+    if (!g_ctx) {
+        fprintf(stderr, "[qwen3-tts-cpp] ERROR: model not loaded\n");
+        return 1;
+    }
+    if (!cb) {
+        fprintf(stderr, "[qwen3-tts-cpp] ERROR: stream callback is null\n");
+        return 2;
+    }
+    if (!text || text[0] == '\0') {
+        fprintf(stderr, "[qwen3-tts-cpp] ERROR: text is required\n");
+        return 4;
+    }
+    qt_tts_params tp;
+    fill_params(&tp, text, lang, instruct, speaker, ref_samples, ref_n,
+                ref_text, seed, temperature, top_k, top_p, repetition_penalty,
+                max_new_tokens);
+    // qt_audio_chunk_cb has the identical signature to qt3_chunk_cb
+    // (bool vs int return are ABI-compatible; non-zero == true).
+    tp.on_chunk = (qt_audio_chunk_cb)cb;
+    tp.on_chunk_user_data = user_data;
+
+    qt_audio out = {0}; // stays empty in streaming mode
+    enum qt_status rc = qt_synthesize(g_ctx, &tp, &out);
+    qt_audio_free(&out);
+    if (rc != QT_STATUS_OK && rc != QT_STATUS_CANCELLED) {
+        fprintf(stderr, "[qwen3-tts-cpp] ERROR: stream synth failed (rc=%d): %s\n",
+                (int)rc, qt_last_error());
+        return 3;
+    }
+    return 0;
+}
+
+void qt3_pcm_free(float *p) { free(p); }
+
+void qt3_unload(void) {
+    if (g_ctx) {
+        qt_free(g_ctx);
+        g_ctx = nullptr;
+    }
+}
+
+int qt3_n_speakers(void) { return g_ctx ? qt_n_speakers(g_ctx) : 0; }
+
+const char *qt3_speaker_name(int i) {
+    return g_ctx ? qt_speaker_name(g_ctx, i) : nullptr;
+}

backend/go/qwen3-tts-cpp/cpp/goqwen3ttscpp.h

@@ -1,12 +1,47 @@
 #pragma once
 
-#include <cstddef>
-#include <cstdint>
-
 extern "C" {
-int load_model(const char *model_dir, int n_threads);
-int synthesize(const char *text, const char *ref_audio_path, const char *dst,
-               const char *language, float temperature, float top_p,
-               int top_k, float repetition_penalty, int max_audio_tokens,
-               int n_threads);
+
+// Streaming PCM chunk callback. samples is mono float PCM at 24 kHz, valid
+// only for the duration of the call. Return non-zero to continue, 0 to abort.
+typedef int (*qt3_chunk_cb)(const float *samples, int n_samples,
+                            void *user_data);
+
+// Load the talker + codec/tokenizer GGUFs. use_fa / clamp_fp16 map to
+// qt_init_params (the qt ABI exposes no thread count; ggml uses its own
+// default). Returns 0 on success, non-zero on failure.
+int qt3_load(const char *talker_path, const char *codec_path, int use_fa,
+             int clamp_fp16);
+
+// Synthesize to a malloc'd float PCM buffer (caller frees via qt3_pcm_free).
+// The synthesis mode (base / custom_voice / voice_design) is auto-detected by
+// qt from the talker GGUF; speaker is honoured only for custom_voice, instruct
+// for voice_design / custom_voice, and ref_samples (+ optional ref_text) drive
+// base-mode cloning. qt enforces the rules and we surface qt_last_error() on
+// QT_STATUS_MODE_INVALID. Writes the sample count to *out_n. Returns NULL on
+// failure (out_n set to 0).
+float *qt3_tts(const char *text, const char *lang, const char *instruct,
+               const char *speaker, const float *ref_samples, int ref_n,
+               const char *ref_text, long long seed, float temperature,
+               int top_k, float top_p, float repetition_penalty,
+               int max_new_tokens, int *out_n);
+
+// Streaming synthesis: cb is invoked per PCM chunk as audio is produced. Same
+// param semantics as qt3_tts. Returns 0 on success.
+int qt3_tts_stream(const char *text, const char *lang, const char *instruct,
+                   const char *speaker, const float *ref_samples, int ref_n,
+                   const char *ref_text, long long seed, float temperature,
+                   int top_k, float top_p, float repetition_penalty,
+                   int max_new_tokens, qt3_chunk_cb cb, void *user_data);
+
+// Free a buffer returned by qt3_tts.
+void qt3_pcm_free(float *p);
+
+// Release the qt context.
+void qt3_unload(void);
+
+// Named-speaker introspection (custom_voice models). Returns 0 / NULL when no
+// model is loaded or the index is out of range.
+int qt3_n_speakers(void);
+const char *qt3_speaker_name(int i);
 }

backend/go/qwen3-tts-cpp/e2e_test.go

@@ -0,0 +1,95 @@
+package main
+
+import (
+	"math"
+	"os"
+	"strings"
+
+	"github.com/ebitengine/purego"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+func ttsReq(text, voice string, lang *string, dst string) *pb.TTSRequest {
+	return &pb.TTSRequest{Text: text, Voice: voice, Language: lang, Dst: dst}
+}
+
+var _ = Describe("qwen3-tts-cpp e2e", Label("e2e"), func() {
+	var loaded bool
+
+	BeforeEach(func() {
+		modelPath := os.Getenv("QWEN3TTS_MODEL")
+		codecPath := os.Getenv("QWEN3TTS_CODEC")
+		if modelPath == "" || codecPath == "" {
+			Skip("QWEN3TTS_MODEL / QWEN3TTS_CODEC not set; skipping e2e")
+		}
+		if !loaded {
+			lib := os.Getenv("QWEN3TTS_LIBRARY")
+			if lib == "" {
+				lib = "./libgoqwen3ttscpp-fallback.so"
+			}
+			h, err := purego.Dlopen(lib, purego.RTLD_NOW|purego.RTLD_GLOBAL)
+			Expect(err).ToNot(HaveOccurred())
+			purego.RegisterLibFunc(&CppLoad, h, "qt3_load")
+			purego.RegisterLibFunc(&CppTTS, h, "qt3_tts")
+			purego.RegisterLibFunc(&CppTTSStream, h, "qt3_tts_stream")
+			purego.RegisterLibFunc(&CppPCMFree, h, "qt3_pcm_free")
+			purego.RegisterLibFunc(&CppUnload, h, "qt3_unload")
+			Expect(CppLoad(modelPath, codecPath, 1, 0)).To(Equal(0))
+			loaded = true
+		}
+	})
+
+	It("synthesizes a WAV file via TTS", func() {
+		b := &Qwen3TtsCpp{opts: loadOptions{seed: 42, useFA: true}}
+		dst := GinkgoT().TempDir() + "/out.wav"
+		lang := "english"
+		err := b.TTS(ttsReq("Hello world.", "", &lang, dst))
+		Expect(err).ToNot(HaveOccurred())
+		fi, err := os.Stat(dst)
+		Expect(err).ToNot(HaveOccurred())
+		Expect(fi.Size()).To(BeNumerically(">", int64(44)))
+	})
+
+	It("streams audio chunks via TTSStream", func() {
+		b := &Qwen3TtsCpp{opts: loadOptions{seed: 42, useFA: true}}
+		results := make(chan []byte, 1024)
+		lang := "english"
+		done := make(chan error, 1)
+		go func() { done <- b.TTSStream(ttsReq("Hello there, streaming test.", "", &lang, ""), results) }()
+
+		var chunks int
+		var first []byte
+		for c := range results {
+			if chunks == 0 {
+				first = c
+			}
+			chunks++
+		}
+		Expect(<-done).ToNot(HaveOccurred())
+		Expect(chunks).To(BeNumerically(">=", 2))
+		Expect(string(first[0:4])).To(Equal("RIFF"))
+		Expect(strings.HasPrefix(string(first[8:12]), "WAVE")).To(BeTrue())
+	})
+
+	It("clones a voice from the config audio_path reference", func() {
+		// 1s of 24kHz mono audio as a clone reference; the base model carries
+		// a speaker encoder, so audio_path drives x-vector voice cloning.
+		ref := GinkgoT().TempDir() + "/ref.wav"
+		samples := make([]float32, qwen3ttsSampleRate)
+		for i := range samples {
+			samples[i] = float32(0.05 * math.Sin(float64(i)*0.06))
+		}
+		Expect(writeWAV24k(ref, samples)).To(Succeed())
+
+		b := &Qwen3TtsCpp{opts: loadOptions{seed: 42, useFA: true}, audioPath: ref}
+		dst := GinkgoT().TempDir() + "/clone.wav"
+		lang := "english"
+		// Empty Voice -> the config audio_path is used as the clone reference.
+		Expect(b.TTS(ttsReq("Cloned voice test.", "", &lang, dst))).To(Succeed())
+		fi, err := os.Stat(dst)
+		Expect(err).ToNot(HaveOccurred())
+		Expect(fi.Size()).To(BeNumerically(">", int64(44)))
+	})
+})

backend/go/qwen3-tts-cpp/goqwen3ttscpp.go

@@ -5,108 +5,225 @@ import (
 	"os"
 	"path/filepath"
 	"strings"
+	"sync"
+	"unsafe"
 
+	"github.com/ebitengine/purego"
 	"github.com/mudler/LocalAI/pkg/grpc/base"
 	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
 )
 
 var (
-	CppLoadModel  func(modelDir string, nThreads int) int
-	CppSynthesize func(text, refAudioPath, dst, language string,
-		temperature, topP float32, topK int,
-		repetitionPenalty float32, maxAudioTokens, nThreads int) int
+	// qt3_load(talker_path, codec_path, use_fa, clamp_fp16) int
+	CppLoad func(talkerPath, codecPath string, useFA, clampFP16 int) int
+	// qt3_tts(text, lang, instruct, speaker, ref_samples, ref_n, ref_text,
+	//         seed, temperature, top_k, top_p, rep_pen, max_new, out_n) -> float*
+	CppTTS func(text, lang, instruct, speaker string, refSamples unsafe.Pointer,
+		refN int, refText string, seed int64, temperature float32, topK int,
+		topP, repPen float32, maxNew int, outN unsafe.Pointer) uintptr
+	// qt3_tts_stream(..., cb, user) int
+	CppTTSStream func(text, lang, instruct, speaker string, refSamples unsafe.Pointer,
+		refN int, refText string, seed int64, temperature float32, topK int,
+		topP, repPen float32, maxNew int, cb uintptr, user uintptr) int
+	CppPCMFree func(ptr uintptr)
+	CppUnload  func()
 )
 
 type Qwen3TtsCpp struct {
 	base.SingleThread
-	threads int
-}
-
-// languageNameAliases maps common full language names to the canonical
-// two-letter code understood by the C++ language_to_id table.
-var languageNameAliases = map[string]string{
-	"english":    "en",
-	"russian":    "ru",
-	"chinese":    "zh",
-	"japanese":   "ja",
-	"korean":     "ko",
-	"german":     "de",
-	"french":     "fr",
-	"spanish":    "es",
-	"italian":    "it",
-	"portuguese": "pt",
-}
-
-// normalizeLanguage coerces a caller-supplied language into the canonical code
-// the model expects. It lowercases, trims, strips any region/locale suffix
-// (en-US, en_US, ja.JP -> en/ja), and resolves common full names (english -> en).
-// An empty input stays empty so the C++ side applies its English default; an
-// unrecognized value is returned normalized so C++ can log it and default.
-func normalizeLanguage(lang string) string {
-	lang = strings.ToLower(strings.TrimSpace(lang))
-	if lang == "" {
-		return ""
-	}
-
-	// Strip region/locale suffix: keep the segment before the first separator.
-	if i := strings.IndexAny(lang, "-_."); i >= 0 {
-		lang = lang[:i]
-	}
-
-	if code, ok := languageNameAliases[lang]; ok {
-		return code
-	}
-	return lang
+	opts loadOptions
+	// audioPath is the model-config reference voice (tts.audio_path), the
+	// default clone reference when a request omits an audio Voice.
+	audioPath string
 }
 
 func (q *Qwen3TtsCpp) Load(opts *pb.ModelOptions) error {
-	// ModelFile is the model directory path (containing GGUF files)
-	modelDir := opts.ModelFile
-	if modelDir == "" {
-		modelDir = opts.ModelPath
+	model := opts.ModelFile
+	if model == "" {
+		model = opts.ModelPath
+	}
+	if !filepath.IsAbs(model) && opts.ModelPath != "" {
+		model = filepath.Join(opts.ModelPath, model)
 	}
 
-	// Resolve relative paths
-	if !filepath.IsAbs(modelDir) && opts.ModelPath != "" {
-		modelDir = filepath.Join(opts.ModelPath, modelDir)
+	q.opts = parseOptions(opts.Options)
+
+	// Resolve the codec/tokenizer GGUF: explicit option, else auto-discover a
+	// *tokenizer*.gguf sibling of the talker model.
+	codec := q.opts.codecPath
+	if codec != "" && !filepath.IsAbs(codec) {
+		codec = filepath.Join(filepath.Dir(model), codec)
+	}
+	if codec == "" {
+		codec = discoverTokenizer(filepath.Dir(model))
+	}
+	if codec == "" {
+		return fmt.Errorf("qwen3-tts: no codec/tokenizer GGUF found; set option 'tokenizer:<file>'")
+	}
+	q.opts.codecPath = codec
+
+	q.audioPath = opts.AudioPath
+	if q.audioPath != "" && !filepath.IsAbs(q.audioPath) {
+		q.audioPath = filepath.Join(filepath.Dir(model), q.audioPath)
 	}
 
-	threads := int(opts.Threads)
-	if threads <= 0 {
-		threads = 4
+	useFA := boolToInt(q.opts.useFA)
+	clamp := boolToInt(q.opts.clampFP16)
+
+	fmt.Fprintf(os.Stderr, "[qwen3-tts-cpp] Load talker=%s codec=%s use_fa=%d clamp_fp16=%d\n",
+		model, codec, useFA, clamp)
+
+	if rc := CppLoad(model, codec, useFA, clamp); rc != 0 {
+		return fmt.Errorf("qwen3-tts: failed to load model (rc=%d)", rc)
 	}
-	q.threads = threads
-
-	fmt.Fprintf(os.Stderr, "[qwen3-tts-cpp] Loading models from: %s (threads=%d)\n", modelDir, threads)
-
-	if ret := CppLoadModel(modelDir, threads); ret != 0 {
-		return fmt.Errorf("failed to load qwen3-tts model (error code: %d)", ret)
-	}
-
 	return nil
 }
 
+// discoverTokenizer returns the first *tokenizer*.gguf in dir, or "".
+func discoverTokenizer(dir string) string {
+	entries, err := os.ReadDir(dir)
+	if err != nil {
+		return ""
+	}
+	for _, e := range entries {
+		name := strings.ToLower(e.Name())
+		if strings.Contains(name, "tokenizer") && strings.HasSuffix(name, ".gguf") {
+			return filepath.Join(dir, e.Name())
+		}
+	}
+	return ""
+}
+
+func boolToInt(b bool) int {
+	if b {
+		return 1
+	}
+	return 0
+}
+
+func optStr(p *string) string {
+	if p == nil {
+		return ""
+	}
+	return *p
+}
+
+// resolveRequest derives the synthesis inputs from a TTSRequest:
+// language, instruct, speaker, ref-audio samples, ref-text and sampling.
+func (q *Qwen3TtsCpp) resolveRequest(req *pb.TTSRequest) (lang, instruct, speaker, refText string, ref []float32, s sampling, err error) {
+	lang = normalizeLanguage(optStr(req.Language))
+	instruct = optStr(req.Instructions)
+
+	var refPath string
+	speaker, refPath = resolveVoice(req.Voice)
+	if refPath == "" && speaker == "" && q.audioPath != "" {
+		// No per-request voice: fall back to the config clone reference.
+		refPath = q.audioPath
+	}
+	if refPath != "" {
+		ref, err = readWAVAsFloat(refPath)
+		if err != nil {
+			return
+		}
+	}
+
+	if req.Params != nil {
+		refText = req.Params["ref_text"]
+	}
+	s = parseSampling(req.Params, q.opts.seed)
+	return
+}
+
 func (q *Qwen3TtsCpp) TTS(req *pb.TTSRequest) error {
-	text := req.Text
-	voice := req.Voice // reference audio path for voice cloning (empty = no cloning)
-	dst := req.Dst
-	language := ""
-	if req.Language != nil {
-		language = normalizeLanguage(*req.Language)
+	if req.Dst == "" {
+		return fmt.Errorf("qwen3-tts: TTS requires a destination path")
+	}
+	if req.Text == "" {
+		return fmt.Errorf("qwen3-tts: TTS requires text")
+	}
+	lang, instruct, speaker, refText, ref, s, err := q.resolveRequest(req)
+	if err != nil {
+		return err
+	}
+	var refPtr unsafe.Pointer
+	if len(ref) > 0 {
+		refPtr = unsafe.Pointer(&ref[0])
 	}
 
-	// Synthesis parameters with sensible defaults
-	temperature := float32(0.9)
-	topP := float32(0.8)
-	topK := 50
-	repetitionPenalty := float32(1.05)
-	maxAudioTokens := 4096
+	var n int32
+	ptr := CppTTS(req.Text, lang, instruct, speaker, refPtr, len(ref), refText,
+		s.seed, s.temperature, s.topK, s.topP, s.repPen, s.maxNew, unsafe.Pointer(&n))
+	runtimeKeepAlive(ref)
+	if ptr == 0 {
+		return fmt.Errorf("qwen3-tts: synthesis failed")
+	}
+	// Register the free as soon as we own a non-null buffer, so the n<=0 guard
+	// below cannot leak it (defensive: the C contract returns NULL on failure).
+	defer CppPCMFree(ptr)
+	if n <= 0 {
+		return fmt.Errorf("qwen3-tts: synthesis produced no samples")
+	}
+	src := unsafe.Slice((*float32)(unsafe.Pointer(ptr)), int(n)) //nolint:govet // C-allocated PCM, copied out before free
+	out := make([]float32, int(n))
+	copy(out, src)
+	return writeWAV24k(req.Dst, out)
+}
 
-	if ret := CppSynthesize(text, voice, dst, language,
-		temperature, topP, topK, repetitionPenalty,
-		maxAudioTokens, q.threads); ret != 0 {
-		return fmt.Errorf("failed to synthesize audio (error code: %d)", ret)
+// streamState carries the active TTSStream channel to the single shared C
+// callback. base.SingleThread serializes TTS/TTSStream, so one global slot is
+// safe and avoids leaking a purego callback per request (purego callbacks
+// cannot be freed and are capped).
+var (
+	streamMu     sync.Mutex
+	streamChan   chan []byte
+	streamCbOnce sync.Once
+	streamCbPtr  uintptr
+)
+
+// streamCallback is registered once and forwards each PCM chunk to streamChan.
+func streamCallback(samples *float32, nSamples int32, _ uintptr) uintptr {
+	if nSamples <= 0 || samples == nil || streamChan == nil {
+		return 1 // continue
+	}
+	src := unsafe.Slice(samples, int(nSamples))
+	cp := make([]float32, int(nSamples)) // copy out of C memory before returning
+	copy(cp, src)
+	streamChan <- floatToPCM16LE(cp)
+	return 1 // continue
+}
+
+func (q *Qwen3TtsCpp) TTSStream(req *pb.TTSRequest, results chan []byte) error {
+	defer close(results)
+	if req.Text == "" {
+		return fmt.Errorf("qwen3-tts: TTSStream requires text")
 	}
 
+	streamCbOnce.Do(func() {
+		streamCbPtr = purego.NewCallback(streamCallback)
+	})
+
+	lang, instruct, speaker, refText, ref, s, err := q.resolveRequest(req)
+	if err != nil {
+		return err
+	}
+	var refPtr unsafe.Pointer
+	if len(ref) > 0 {
+		refPtr = unsafe.Pointer(&ref[0])
+	}
+
+	// Emit the WAV header first so the HTTP layer gets a self-describing stream.
+	results <- wavHeader24k()
+
+	streamMu.Lock()
+	streamChan = results
+	rc := CppTTSStream(req.Text, lang, instruct, speaker, refPtr, len(ref), refText,
+		s.seed, s.temperature, s.topK, s.topP, s.repPen, s.maxNew, streamCbPtr, 0)
+	streamChan = nil
+	streamMu.Unlock()
+	runtimeKeepAlive(ref)
+
+	if rc != 0 {
+		return fmt.Errorf("qwen3-tts: streaming synthesis failed (rc=%d)", rc)
+	}
 	return nil
 }

backend/go/qwen3-tts-cpp/language_test.go

@@ -1,53 +0,0 @@
-package main
-
-import (
-	"testing"
-
-	. "github.com/onsi/ginkgo/v2"
-	. "github.com/onsi/gomega"
-)
-
-func TestLanguageNormalization(t *testing.T) {
-	RegisterFailHandler(Fail)
-	RunSpecs(t, "qwen3-tts-cpp language normalization")
-}
-
-var _ = Describe("normalizeLanguage", func() {
-	DescribeTable("maps caller input to the canonical model language code",
-		func(input, expected string) {
-			Expect(normalizeLanguage(input)).To(Equal(expected))
-		},
-		// Canonical codes pass through unchanged
-		Entry("canonical en", "en", "en"),
-		Entry("canonical zh", "zh", "zh"),
-		Entry("canonical pt", "pt", "pt"),
-
-		// Case-insensitive
-		Entry("uppercase", "EN", "en"),
-		Entry("mixed case", "Ja", "ja"),
-
-		// Surrounding whitespace
-		Entry("trims whitespace", "  en  ", "en"),
-
-		// Region/locale stripping
-		Entry("BCP-47 region", "en-US", "en"),
-		Entry("underscore region", "en_US", "en"),
-		Entry("dotted locale", "ja.JP", "ja"),
-		Entry("region + case", "ZH-CN", "zh"),
-
-		// Full-name aliases
-		Entry("english name", "english", "en"),
-		Entry("chinese name cased", "Chinese", "zh"),
-		Entry("japanese name", "japanese", "ja"),
-		Entry("russian name", "russian", "ru"),
-		Entry("portuguese name", "portuguese", "pt"),
-
-		// Empty stays empty (C++ applies the English default)
-		Entry("empty", "", ""),
-		Entry("whitespace only", "   ", ""),
-
-		// Unknown values pass through normalized so C++ can log + default
-		Entry("unknown code", "klingon", "klingon"),
-		Entry("unknown with region", "xx-YY", "xx"),
-	)
-})

backend/go/qwen3-tts-cpp/main.go

@@ -19,24 +19,25 @@ type LibFuncs struct {
 }
 
 func main() {
-	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("QWEN3TTS_LIBRARY")
 	if libName == "" {
 		libName = "./libgoqwen3ttscpp-fallback.so"
 	}
 
-	gosd, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
+	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {
 		panic(err)
 	}
 
 	libFuncs := []LibFuncs{
-		{&CppLoadModel, "load_model"},
-		{&CppSynthesize, "synthesize"},
+		{&CppLoad, "qt3_load"},
+		{&CppTTS, "qt3_tts"},
+		{&CppTTSStream, "qt3_tts_stream"},
+		{&CppPCMFree, "qt3_pcm_free"},
+		{&CppUnload, "qt3_unload"},
 	}
-
 	for _, lf := range libFuncs {
-		purego.RegisterLibFunc(lf.FuncPtr, gosd, lf.Name)
+		purego.RegisterLibFunc(lf.FuncPtr, lib, lf.Name)
 	}
 
 	flag.Parse()

backend/go/qwen3-tts-cpp/options.go

@@ -0,0 +1,161 @@
+package main
+
+import (
+	"strconv"
+	"strings"
+)
+
+// loadOptions holds the parsed model-level options.
+type loadOptions struct {
+	codecPath string
+	useFA     bool
+	clampFP16 bool
+	seed      int64
+}
+
+// sampling holds per-request generation parameters with qt defaults applied.
+type sampling struct {
+	temperature float32
+	topK        int
+	topP        float32
+	repPen      float32
+	maxNew      int
+	seed        int64
+}
+
+func splitOption(o string) (key, value string, ok bool) {
+	i := strings.Index(o, ":")
+	if i < 0 {
+		return "", "", false
+	}
+	return strings.TrimSpace(o[:i]), strings.TrimSpace(o[i+1:]), true
+}
+
+func parseBool(v string) bool { return v == "true" || v == "1" }
+
+// parseOptions reads the backend "key:value" option slice. Unknown keys are
+// ignored. Defaults: use_fa true (qt default; CPU still uses the F32 chain),
+// seed -1 (engine random).
+func parseOptions(opts []string) loadOptions {
+	o := loadOptions{useFA: true, seed: -1}
+	for _, oo := range opts {
+		key, value, ok := splitOption(oo)
+		if !ok {
+			continue
+		}
+		switch key {
+		case "tokenizer", "codec":
+			o.codecPath = value
+		case "use_fa":
+			o.useFA = parseBool(value)
+		case "clamp_fp16":
+			o.clampFP16 = parseBool(value)
+		case "seed":
+			if n, err := strconv.ParseInt(value, 10, 64); err == nil {
+				o.seed = n
+			}
+		}
+	}
+	return o
+}
+
+// languageAliases maps codes / locales / full names to the upstream qwentts
+// language names. "auto" (and empty) map to "" so the engine auto-detects.
+var languageAliases = map[string]string{
+	"en": "english", "english": "english",
+	"zh": "chinese", "chinese": "chinese", "mandarin": "chinese",
+	"ja": "japanese", "japanese": "japanese",
+	"ko": "korean", "korean": "korean",
+	"de": "german", "german": "german",
+	"fr": "french", "french": "french",
+	"es": "spanish", "spanish": "spanish",
+	"it": "italian", "italian": "italian",
+	"pt": "portuguese", "portuguese": "portuguese",
+	"ru": "russian", "russian": "russian",
+	"auto": "",
+}
+
+// normalizeLanguage lowercases, trims, strips a region/locale suffix
+// (en-US -> en), and resolves to the qwentts language name. Empty stays empty
+// (engine auto-detects); an unknown value passes through normalized.
+func normalizeLanguage(lang string) string {
+	lang = strings.ToLower(strings.TrimSpace(lang))
+	if lang == "" {
+		return ""
+	}
+	if i := strings.IndexAny(lang, "-_."); i >= 0 {
+		lang = lang[:i]
+	}
+	if v, ok := languageAliases[lang]; ok {
+		return v
+	}
+	return lang
+}
+
+var refAudioExts = []string{".wav", ".flac", ".mp3", ".ogg", ".m4a"}
+
+// resolveVoice interprets the request Voice field: a value ending in a known
+// audio extension is a clone-reference path; anything else is a named speaker
+// (custom_voice). Empty input yields no speaker and no reference.
+func resolveVoice(voice string) (speaker, refPath string) {
+	v := strings.TrimSpace(voice)
+	if v == "" {
+		return "", ""
+	}
+	lower := strings.ToLower(v)
+	for _, ext := range refAudioExts {
+		if strings.HasSuffix(lower, ext) {
+			return "", v
+		}
+	}
+	return v, ""
+}
+
+func parseFloat32(v string, def float32) float32 {
+	if v == "" {
+		return def
+	}
+	f, err := strconv.ParseFloat(v, 32)
+	if err != nil {
+		return def
+	}
+	return float32(f)
+}
+
+func parseInt(v string, def int) int {
+	if v == "" {
+		return def
+	}
+	n, err := strconv.Atoi(v)
+	if err != nil {
+		return def
+	}
+	return n
+}
+
+func parseInt64(v string, def int64) int64 {
+	if v == "" {
+		return def
+	}
+	n, err := strconv.ParseInt(v, 10, 64)
+	if err != nil {
+		return def
+	}
+	return n
+}
+
+// parseSampling reads per-request sampling params from the TTSRequest params
+// map, applying qt defaults (matching qt_tts_default_params).
+func parseSampling(params map[string]string, defaultSeed int64) sampling {
+	s := sampling{temperature: 0.9, topK: 50, topP: 1.0, repPen: 1.05, maxNew: 2048, seed: defaultSeed}
+	if params == nil {
+		return s
+	}
+	s.temperature = parseFloat32(params["temperature"], s.temperature)
+	s.topK = parseInt(params["top_k"], s.topK)
+	s.topP = parseFloat32(params["top_p"], s.topP)
+	s.repPen = parseFloat32(params["repetition_penalty"], s.repPen)
+	s.maxNew = parseInt(params["max_new_tokens"], s.maxNew)
+	s.seed = parseInt64(params["seed"], s.seed)
+	return s
+}

backend/go/qwen3-tts-cpp/qwen3ttscpp_test.go

@@ -1,173 +1,136 @@
 package main
 
 import (
-	"context"
-	"os"
-	"os/exec"
-	"path/filepath"
+	"bytes"
+	"encoding/binary"
 	"testing"
-	"time"
 
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
-	"google.golang.org/grpc"
-	"google.golang.org/grpc/credentials/insecure"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
 )
 
-const (
-	testAddr    = "localhost:50051"
-	startupWait = 5 * time.Second
-)
-
-func skipIfNoModel(t *testing.T) string {
-	t.Helper()
-	modelDir := os.Getenv("QWEN3TTS_MODEL_DIR")
-	if modelDir == "" {
-		t.Skip("QWEN3TTS_MODEL_DIR not set, skipping test (set to directory with GGUF models)")
-	}
-	if _, err := os.Stat(filepath.Join(modelDir, "qwen3-tts-0.6b-f16.gguf")); os.IsNotExist(err) {
-		t.Skipf("TTS model file not found in %s, skipping", modelDir)
-	}
-	if _, err := os.Stat(filepath.Join(modelDir, "qwen3-tts-tokenizer-f16.gguf")); os.IsNotExist(err) {
-		t.Skipf("Tokenizer model file not found in %s, skipping", modelDir)
-	}
-	return modelDir
+func TestQwen3TtsCpp(t *testing.T) {
+	RegisterFailHandler(Fail)
+	RunSpecs(t, "qwen3-tts-cpp suite")
 }
 
-func startServer(t *testing.T) *exec.Cmd {
-	t.Helper()
-	binary := os.Getenv("QWEN3TTS_BINARY")
-	if binary == "" {
-		binary = "./qwen3-tts-cpp"
-	}
-	if _, err := os.Stat(binary); os.IsNotExist(err) {
-		t.Skipf("Backend binary not found at %s, skipping", binary)
-	}
-	cmd := exec.Command(binary, "--addr", testAddr)
-	cmd.Stdout = os.Stderr
-	cmd.Stderr = os.Stderr
-	if err := cmd.Start(); err != nil {
-		t.Fatalf("Failed to start server: %v", err)
-	}
-	time.Sleep(startupWait)
-	return cmd
-}
-
-func stopServer(cmd *exec.Cmd) {
-	if cmd != nil && cmd.Process != nil {
-		cmd.Process.Kill()
-		cmd.Wait()
-	}
-}
-
-func dialGRPC(t *testing.T) *grpc.ClientConn {
-	t.Helper()
-	conn, err := grpc.Dial(testAddr,
-		grpc.WithTransportCredentials(insecure.NewCredentials()),
-		grpc.WithDefaultCallOptions(
-			grpc.MaxCallRecvMsgSize(50*1024*1024),
-			grpc.MaxCallSendMsgSize(50*1024*1024),
-		),
+var _ = Describe("normalizeLanguage", func() {
+	DescribeTable("maps caller language to qwentts language names",
+		func(in, want string) {
+			Expect(normalizeLanguage(in)).To(Equal(want))
+		},
+		Entry("empty stays empty", "", ""),
+		Entry("auto maps to empty", "auto", ""),
+		Entry("english full name", "English", "english"),
+		Entry("english code", "en", "english"),
+		Entry("locale suffix stripped", "en-US", "english"),
+		Entry("underscore locale", "zh_CN", "chinese"),
+		Entry("mandarin alias", "mandarin", "chinese"),
+		Entry("japanese already full", "japanese", "japanese"),
+		Entry("unknown passes through normalized", "xx", "xx"),
 	)
-	if err != nil {
-		t.Fatalf("Failed to dial gRPC: %v", err)
-	}
-	return conn
-}
+})
 
-func TestServerHealth(t *testing.T) {
-	cmd := startServer(t)
-	defer stopServer(cmd)
-
-	conn := dialGRPC(t)
-	defer conn.Close()
-
-	client := pb.NewBackendClient(conn)
-	resp, err := client.Health(context.Background(), &pb.HealthMessage{})
-	if err != nil {
-		t.Fatalf("Health check failed: %v", err)
-	}
-	if string(resp.Message) != "OK" {
-		t.Fatalf("Expected OK, got %s", string(resp.Message))
-	}
-}
-
-func TestLoadModel(t *testing.T) {
-	modelDir := skipIfNoModel(t)
-	cmd := startServer(t)
-	defer stopServer(cmd)
-
-	conn := dialGRPC(t)
-	defer conn.Close()
-
-	client := pb.NewBackendClient(conn)
-
-	resp, err := client.LoadModel(context.Background(), &pb.ModelOptions{
-		ModelFile: modelDir,
-		Threads:   4,
+var _ = Describe("resolveVoice", func() {
+	It("treats a bare token as a named speaker", func() {
+		sp, ref := resolveVoice("serena")
+		Expect(sp).To(Equal("serena"))
+		Expect(ref).To(BeEmpty())
 	})
-	if err != nil {
-		t.Fatalf("LoadModel failed: %v", err)
-	}
-	if !resp.Success {
-		t.Fatalf("LoadModel returned failure: %s", resp.Message)
-	}
-}
-
-func TestTTS(t *testing.T) {
-	modelDir := skipIfNoModel(t)
-
-	tmpDir, err := os.MkdirTemp("", "qwen3tts-test")
-	if err != nil {
-		t.Fatal(err)
-	}
-	t.Cleanup(func() { os.RemoveAll(tmpDir) })
-
-	outputFile := filepath.Join(tmpDir, "output.wav")
-
-	cmd := startServer(t)
-	defer stopServer(cmd)
-
-	conn := dialGRPC(t)
-	defer conn.Close()
-
-	client := pb.NewBackendClient(conn)
-
-	// Load models
-	loadResp, err := client.LoadModel(context.Background(), &pb.ModelOptions{
-		ModelFile: modelDir,
-		Threads:   4,
+	It("treats an audio path as a clone reference (case-insensitive ext)", func() {
+		sp, ref := resolveVoice("/x/ref.WAV")
+		Expect(sp).To(BeEmpty())
+		Expect(ref).To(Equal("/x/ref.WAV"))
 	})
-	if err != nil {
-		t.Fatalf("LoadModel failed: %v", err)
-	}
-	if !loadResp.Success {
-		t.Fatalf("LoadModel returned failure: %s", loadResp.Message)
-	}
-
-	// Synthesize speech
-	language := "en"
-	_, err = client.TTS(context.Background(), &pb.TTSRequest{
-		Text:     "Hello, this is a test of the Qwen3 text to speech system.",
-		Dst:      outputFile,
-		Language: &language,
+	It("recognizes mp3/flac/ogg/m4a", func() {
+		for _, p := range []string{"a.mp3", "b.flac", "c.ogg", "d.m4a"} {
+			sp, ref := resolveVoice(p)
+			Expect(sp).To(BeEmpty())
+			Expect(ref).To(Equal(p))
+		}
 	})
-	if err != nil {
-		t.Fatalf("TTS failed: %v", err)
-	}
+	It("returns empty for empty input", func() {
+		sp, ref := resolveVoice("  ")
+		Expect(sp).To(BeEmpty())
+		Expect(ref).To(BeEmpty())
+	})
+})
 
-	// Verify output file exists and has content
-	info, err := os.Stat(outputFile)
-	if os.IsNotExist(err) {
-		t.Fatal("Output audio file was not created")
-	}
-	if err != nil {
-		t.Fatalf("Failed to stat output file: %v", err)
-	}
+var _ = Describe("parseOptions", func() {
+	It("extracts codec, use_fa, clamp_fp16, seed", func() {
+		o := parseOptions([]string{
+			"tokenizer:tok.gguf", "use_fa:false", "clamp_fp16:true",
+			"seed:7", "unknown:ignored",
+		})
+		Expect(o.codecPath).To(Equal("tok.gguf"))
+		Expect(o.useFA).To(BeFalse())
+		Expect(o.clampFP16).To(BeTrue())
+		Expect(o.seed).To(Equal(int64(7)))
+	})
+	It("accepts codec: as an alias for tokenizer:", func() {
+		Expect(parseOptions([]string{"codec:c.gguf"}).codecPath).To(Equal("c.gguf"))
+	})
+	It("defaults use_fa true and seed -1", func() {
+		o := parseOptions(nil)
+		Expect(o.useFA).To(BeTrue())
+		Expect(o.seed).To(Equal(int64(-1)))
+	})
+})
 
-	t.Logf("Output file size: %d bytes", info.Size())
+var _ = Describe("parseSampling", func() {
+	It("applies qt defaults when params are absent", func() {
+		s := parseSampling(nil, -1)
+		Expect(s.temperature).To(BeNumerically("~", 0.9, 1e-6))
+		Expect(s.topK).To(Equal(50))
+		Expect(s.topP).To(BeNumerically("~", 1.0, 1e-6))
+		Expect(s.repPen).To(BeNumerically("~", 1.05, 1e-6))
+		Expect(s.maxNew).To(Equal(2048))
+		Expect(s.seed).To(Equal(int64(-1)))
+	})
+	It("reads overrides and falls back to default seed", func() {
+		s := parseSampling(map[string]string{
+			"temperature": "0.5", "top_k": "10", "top_p": "0.8",
+			"repetition_penalty": "1.2", "max_new_tokens": "512",
+		}, 99)
+		Expect(s.temperature).To(BeNumerically("~", 0.5, 1e-6))
+		Expect(s.topK).To(Equal(10))
+		Expect(s.topP).To(BeNumerically("~", 0.8, 1e-6))
+		Expect(s.repPen).To(BeNumerically("~", 1.2, 1e-6))
+		Expect(s.maxNew).To(Equal(512))
+		Expect(s.seed).To(Equal(int64(99)))
+	})
+	It("reads an explicit seed override", func() {
+		Expect(parseSampling(map[string]string{"seed": "123"}, -1).seed).To(Equal(int64(123)))
+	})
+})
 
-	// WAV header is 44 bytes minimum; any real audio should be much larger
-	if info.Size() < 1000 {
-		t.Errorf("Output file too small (%d bytes), expected real audio data", info.Size())
-	}
-}
+var _ = Describe("wavHeader24k", func() {
+	It("emits a 44-byte streaming WAV header at 24 kHz mono 16-bit", func() {
+		h := wavHeader24k()
+		Expect(h).To(HaveLen(44))
+		Expect(string(h[0:4])).To(Equal("RIFF"))
+		Expect(string(h[8:12])).To(Equal("WAVE"))
+		Expect(string(h[12:16])).To(Equal("fmt "))
+		Expect(string(h[36:40])).To(Equal("data"))
+		var sampleRate uint32
+		Expect(binary.Read(bytes.NewReader(h[24:28]), binary.LittleEndian, &sampleRate)).To(Succeed())
+		Expect(sampleRate).To(Equal(uint32(24000)))
+	})
+})
+
+var _ = Describe("floatToPCM16LE", func() {
+	It("clamps and converts float PCM to little-endian int16 bytes", func() {
+		b := floatToPCM16LE([]float32{0, 1.0, -1.0, 2.0, -2.0})
+		Expect(b).To(HaveLen(10))
+		read := func(off int) int16 {
+			var v int16
+			_ = binary.Read(bytes.NewReader(b[off:off+2]), binary.LittleEndian, &v)
+			return v
+		}
+		Expect(read(0)).To(Equal(int16(0)))
+		Expect(read(2)).To(Equal(int16(32767)))
+		Expect(read(4)).To(Equal(int16(-32767)))
+		Expect(read(6)).To(Equal(int16(32767)))  // clamped from 2.0
+		Expect(read(8)).To(Equal(int16(-32767))) // clamped from -2.0
+	})
+})

backend/go/qwen3-tts-cpp/test.sh

@@ -2,51 +2,30 @@
 set -e
 
 CURDIR=$(dirname "$(realpath $0)")
+cd "$CURDIR"
 
 echo "Running qwen3-tts-cpp backend tests..."
 
-# The test requires:
-#   - QWEN3TTS_MODEL_DIR: path to directory containing GGUF model files
-#   - QWEN3TTS_BINARY: path to the qwen3-tts-cpp binary (defaults to ./qwen3-tts-cpp)
-#
-# Tests that require the model will be skipped if QWEN3TTS_MODEL_DIR is not set
-# or the directory does not contain the required model files.
-
-cd "$CURDIR"
-
-# Only auto-download models when QWEN3TTS_MODEL_DIR is not explicitly set
-if [ -z "$QWEN3TTS_MODEL_DIR" ]; then
-    export QWEN3TTS_MODEL_DIR="./qwen3-tts-models"
-
-    if [ ! -d "$QWEN3TTS_MODEL_DIR" ]; then
-        echo "Creating qwen3-tts-models directory for tests..."
-        mkdir -p "$QWEN3TTS_MODEL_DIR"
-        REPO_ID="endo5501/qwen3-tts.cpp"
-        echo "Repository: ${REPO_ID}"
-        echo ""
-
-        # Files to download (smallest model for testing)
-        FILES=(
-            "qwen3-tts-0.6b-f16.gguf"
-            "qwen3-tts-tokenizer-f16.gguf"
-        )
-
-        BASE_URL="https://huggingface.co/${REPO_ID}/resolve/main"
-
-        for file in "${FILES[@]}"; do
-            dest="${QWEN3TTS_MODEL_DIR}/${file}"
-            if [ -f "${dest}" ]; then
-                echo "  [skip] ${file} (already exists)"
-            else
-                echo "  [download] ${file}..."
-                curl -L -o "${dest}" "${BASE_URL}/${file}" --progress-bar
-                echo "  [done] ${file}"
-            fi
-        done
-    fi
+# Auto-download a small model pair only when QWEN3TTS_MODEL is not set.
+if [ -z "$QWEN3TTS_MODEL" ]; then
+    MODEL_DIR="./qwen3-tts-models"
+    mkdir -p "$MODEL_DIR"
+    REPO_ID="Serveurperso/Qwen3-TTS-GGUF"
+    BASE_URL="https://huggingface.co/${REPO_ID}/resolve/main"
+    FILES=( "qwen-talker-0.6b-base-Q4_K_M.gguf" "qwen-tokenizer-12hz-Q4_K_M.gguf" )
+    for file in "${FILES[@]}"; do
+        dest="${MODEL_DIR}/${file}"
+        if [ -f "${dest}" ]; then
+            echo "  [skip] ${file}"
+        else
+            echo "  [download] ${file}..."
+            curl -L -o "${dest}" "${BASE_URL}/${file}" --progress-bar
+        fi
+    done
+    export QWEN3TTS_MODEL="${MODEL_DIR}/qwen-talker-0.6b-base-Q4_K_M.gguf"
+    export QWEN3TTS_CODEC="${MODEL_DIR}/qwen-tokenizer-12hz-Q4_K_M.gguf"
 fi
 
-# Run Go tests
-go test -v -timeout 600s .
+go test -v -timeout 1200s .
 
 echo "All qwen3-tts-cpp tests passed."

backend/go/sherpa-onnx/backend.go

@@ -62,7 +62,7 @@ var (
 	shimVadConfigSetDebug                    func(uintptr, int32)
 	shimCreateVad                            func(uintptr, float32) uintptr
 
-	// TTS (offline, VITS) config
+	// TTS (offline, VITS/Piper and Kokoro) config
 	shimTtsConfigNew                  func() uintptr
 	shimTtsConfigFree                 func(uintptr)
 	shimTtsConfigSetVitsModel         func(uintptr, string)
@@ -76,6 +76,14 @@ var (
 	shimTtsConfigSetDebug             func(uintptr, int32)
 	shimTtsConfigSetProvider          func(uintptr, string)
 	shimTtsConfigSetMaxNumSentences   func(uintptr, int32)
+	shimTtsConfigSetKokoroModel       func(uintptr, string)
+	shimTtsConfigSetKokoroVoices      func(uintptr, string)
+	shimTtsConfigSetKokoroTokens      func(uintptr, string)
+	shimTtsConfigSetKokoroDataDir     func(uintptr, string)
+	shimTtsConfigSetKokoroDictDir     func(uintptr, string)
+	shimTtsConfigSetKokoroLexicon     func(uintptr, string)
+	shimTtsConfigSetKokoroLang        func(uintptr, string)
+	shimTtsConfigSetKokoroLengthScale func(uintptr, float32)
 	shimCreateOfflineTts              func(uintptr) uintptr
 
 	// Offline recognizer config
@@ -101,37 +109,37 @@ var (
 	shimCreateOfflineRecognizer                  func(uintptr) uintptr
 
 	// Online recognizer config
-	shimOnlineRecogConfigNew                      func() uintptr
-	shimOnlineRecogConfigFree                     func(uintptr)
-	shimOnlineRecogConfigSetTransducerEncoder     func(uintptr, string)
-	shimOnlineRecogConfigSetTransducerDecoder     func(uintptr, string)
-	shimOnlineRecogConfigSetTransducerJoiner      func(uintptr, string)
-	shimOnlineRecogConfigSetTokens                func(uintptr, string)
-	shimOnlineRecogConfigSetNumThreads            func(uintptr, int32)
-	shimOnlineRecogConfigSetDebug                 func(uintptr, int32)
-	shimOnlineRecogConfigSetProvider              func(uintptr, string)
-	shimOnlineRecogConfigSetFeatSampleRate        func(uintptr, int32)
-	shimOnlineRecogConfigSetFeatFeatureDim        func(uintptr, int32)
-	shimOnlineRecogConfigSetDecodingMethod        func(uintptr, string)
-	shimOnlineRecogConfigSetEnableEndpoint        func(uintptr, int32)
+	shimOnlineRecogConfigNew                        func() uintptr
+	shimOnlineRecogConfigFree                       func(uintptr)
+	shimOnlineRecogConfigSetTransducerEncoder       func(uintptr, string)
+	shimOnlineRecogConfigSetTransducerDecoder       func(uintptr, string)
+	shimOnlineRecogConfigSetTransducerJoiner        func(uintptr, string)
+	shimOnlineRecogConfigSetTokens                  func(uintptr, string)
+	shimOnlineRecogConfigSetNumThreads              func(uintptr, int32)
+	shimOnlineRecogConfigSetDebug                   func(uintptr, int32)
+	shimOnlineRecogConfigSetProvider                func(uintptr, string)
+	shimOnlineRecogConfigSetFeatSampleRate          func(uintptr, int32)
+	shimOnlineRecogConfigSetFeatFeatureDim          func(uintptr, int32)
+	shimOnlineRecogConfigSetDecodingMethod          func(uintptr, string)
+	shimOnlineRecogConfigSetEnableEndpoint          func(uintptr, int32)
 	shimOnlineRecogConfigSetRule1MinTrailingSilence func(uintptr, float32)
 	shimOnlineRecogConfigSetRule2MinTrailingSilence func(uintptr, float32)
 	shimOnlineRecogConfigSetRule3MinUtteranceLength func(uintptr, float32)
-	shimCreateOnlineRecognizer                    func(uintptr) uintptr
+	shimCreateOnlineRecognizer                      func(uintptr) uintptr
 
 	// Result accessors. Pointer returns use unsafe.Pointer so Go's
 	// vet checker doesn't flag them — the returned memory is C-owned,
 	// not subject to Go GC motion.
-	shimWaveSampleRate            func(uintptr) int32
-	shimWaveNumSamples            func(uintptr) int32
-	shimWaveSamples               func(uintptr) unsafe.Pointer
-	shimOfflineResultText         func(uintptr) unsafe.Pointer
-	shimOnlineResultText          func(uintptr) unsafe.Pointer
-	shimGeneratedAudioSampleRate  func(uintptr) int32
-	shimGeneratedAudioN           func(uintptr) int32
-	shimGeneratedAudioSamples     func(uintptr) unsafe.Pointer
-	shimSpeechSegmentStart        func(uintptr) int32
-	shimSpeechSegmentN            func(uintptr) int32
+	shimWaveSampleRate           func(uintptr) int32
+	shimWaveNumSamples           func(uintptr) int32
+	shimWaveSamples              func(uintptr) unsafe.Pointer
+	shimOfflineResultText        func(uintptr) unsafe.Pointer
+	shimOnlineResultText         func(uintptr) unsafe.Pointer
+	shimGeneratedAudioSampleRate func(uintptr) int32
+	shimGeneratedAudioN          func(uintptr) int32
+	shimGeneratedAudioSamples    func(uintptr) unsafe.Pointer
+	shimSpeechSegmentStart       func(uintptr) int32
+	shimSpeechSegmentN           func(uintptr) int32
 
 	// TTS streaming callback trampoline
 	shimTtsGenerateWithCallback func(tts uintptr, text string, sid int32, speed float32, cb uintptr, ud uintptr) uintptr
@@ -161,13 +169,13 @@ var (
 // pointer returned by the shim or `unsafe.Pointer(&slice[0])` from Go.
 var (
 	// VAD
-	sherpaVadAcceptWaveform       func(vad uintptr, samples unsafe.Pointer, n int32)
-	sherpaVadReset                func(vad uintptr)
-	sherpaVadFlush                func(vad uintptr)
-	sherpaVadEmpty                func(vad uintptr) int32
-	sherpaVadFront                func(vad uintptr) uintptr
-	sherpaVadPop                  func(vad uintptr)
-	sherpaDestroySpeechSegment    func(seg uintptr)
+	sherpaVadAcceptWaveform    func(vad uintptr, samples unsafe.Pointer, n int32)
+	sherpaVadReset             func(vad uintptr)
+	sherpaVadFlush             func(vad uintptr)
+	sherpaVadEmpty             func(vad uintptr) int32
+	sherpaVadFront             func(vad uintptr) uintptr
+	sherpaVadPop               func(vad uintptr)
+	sherpaDestroySpeechSegment func(seg uintptr)
 
 	// Wave IO
 	sherpaReadWave  func(filename string) uintptr
@@ -175,11 +183,11 @@ var (
 	sherpaWriteWave func(samples unsafe.Pointer, n int32, sampleRate int32, filename string) int32
 
 	// Offline ASR
-	sherpaCreateOfflineStream           func(rec uintptr) uintptr
-	sherpaDestroyOfflineStream          func(stream uintptr)
-	sherpaAcceptWaveformOffline         func(stream uintptr, sr int32, samples unsafe.Pointer, n int32)
-	sherpaDecodeOfflineStream           func(rec uintptr, stream uintptr)
-	sherpaGetOfflineStreamResult        func(stream uintptr) uintptr
+	sherpaCreateOfflineStream            func(rec uintptr) uintptr
+	sherpaDestroyOfflineStream           func(stream uintptr)
+	sherpaAcceptWaveformOffline          func(stream uintptr, sr int32, samples unsafe.Pointer, n int32)
+	sherpaDecodeOfflineStream            func(rec uintptr, stream uintptr)
+	sherpaGetOfflineStreamResult         func(stream uintptr) uintptr
 	sherpaDestroyOfflineRecognizerResult func(result uintptr)
 
 	// Online ASR
@@ -195,21 +203,21 @@ var (
 	sherpaOnlineStreamInputFinished     func(stream uintptr)
 
 	// TTS
-	sherpaOfflineTtsGenerate             func(tts uintptr, text string, sid int32, speed float32) uintptr
+	sherpaOfflineTtsGenerate              func(tts uintptr, text string, sid int32, speed float32) uintptr
 	sherpaDestroyOfflineTtsGeneratedAudio func(audio uintptr)
-	sherpaOfflineTtsSampleRate           func(tts uintptr) int32
+	sherpaOfflineTtsSampleRate            func(tts uintptr) int32
 
 	// Offline speaker diarization. Result handle owns the segment-array
 	// pointer returned by ResultSortByStartTime; destroy the segment
 	// array first, then the result, then (at backend Free()) the diarizer.
-	sherpaDestroyOfflineSpeakerDiarization                 func(sd uintptr)
-	sherpaOfflineSpeakerDiarizationGetSampleRate           func(sd uintptr) int32
-	sherpaOfflineSpeakerDiarizationProcess                 func(sd uintptr, samples unsafe.Pointer, n int32) uintptr
-	sherpaOfflineSpeakerDiarizationResultGetNumSegments    func(result uintptr) int32
-	sherpaOfflineSpeakerDiarizationResultGetNumSpeakers    func(result uintptr) int32
-	sherpaOfflineSpeakerDiarizationResultSortByStartTime   func(result uintptr) uintptr
-	sherpaOfflineSpeakerDiarizationDestroySegment          func(segs uintptr)
-	sherpaDestroyOfflineSpeakerDiarizationResult           func(result uintptr)
+	sherpaDestroyOfflineSpeakerDiarization               func(sd uintptr)
+	sherpaOfflineSpeakerDiarizationGetSampleRate         func(sd uintptr) int32
+	sherpaOfflineSpeakerDiarizationProcess               func(sd uintptr, samples unsafe.Pointer, n int32) uintptr
+	sherpaOfflineSpeakerDiarizationResultGetNumSegments  func(result uintptr) int32
+	sherpaOfflineSpeakerDiarizationResultGetNumSpeakers  func(result uintptr) int32
+	sherpaOfflineSpeakerDiarizationResultSortByStartTime func(result uintptr) uintptr
+	sherpaOfflineSpeakerDiarizationDestroySegment        func(segs uintptr)
+	sherpaDestroyOfflineSpeakerDiarizationResult         func(result uintptr)
 )
 
 var (
@@ -278,6 +286,14 @@ func loadSherpaLibsOnce() error {
 		{&shimTtsConfigSetDebug, "sherpa_shim_tts_config_set_debug"},
 		{&shimTtsConfigSetProvider, "sherpa_shim_tts_config_set_provider"},
 		{&shimTtsConfigSetMaxNumSentences, "sherpa_shim_tts_config_set_max_num_sentences"},
+		{&shimTtsConfigSetKokoroModel, "sherpa_shim_tts_config_set_kokoro_model"},
+		{&shimTtsConfigSetKokoroVoices, "sherpa_shim_tts_config_set_kokoro_voices"},
+		{&shimTtsConfigSetKokoroTokens, "sherpa_shim_tts_config_set_kokoro_tokens"},
+		{&shimTtsConfigSetKokoroDataDir, "sherpa_shim_tts_config_set_kokoro_data_dir"},
+		{&shimTtsConfigSetKokoroDictDir, "sherpa_shim_tts_config_set_kokoro_dict_dir"},
+		{&shimTtsConfigSetKokoroLexicon, "sherpa_shim_tts_config_set_kokoro_lexicon"},
+		{&shimTtsConfigSetKokoroLang, "sherpa_shim_tts_config_set_kokoro_lang"},
+		{&shimTtsConfigSetKokoroLengthScale, "sherpa_shim_tts_config_set_kokoro_length_scale"},
 		{&shimCreateOfflineTts, "sherpa_shim_create_offline_tts"},
 
 		{&shimOfflineRecogConfigNew, "sherpa_shim_offline_recog_config_new"},
@@ -688,21 +704,14 @@ func (s *SherpaBackend) loadTTS(opts *pb.ModelOptions) error {
 	cfg := shimTtsConfigNew()
 	defer shimTtsConfigFree(cfg)
 
-	shimTtsConfigSetVitsModel(cfg, modelFile)
-
-	if tokensPath := filepath.Join(modelDir, "tokens.txt"); fileExists(tokensPath) {
-		shimTtsConfigSetVitsTokens(cfg, tokensPath)
+	// Kokoro models ship a voices style file alongside the ONNX, whereas
+	// VITS/Piper voices do not. That presence is what tells the two model
+	// families apart, since both arrive as a plain *.onnx in modelDir.
+	if isKokoroModel(modelDir) {
+		s.configureKokoroTTS(cfg, opts, modelFile, modelDir)
+	} else {
+		s.configureVitsTTS(cfg, opts, modelFile, modelDir)
 	}
-	if lexiconPath := filepath.Join(modelDir, "lexicon.txt"); fileExists(lexiconPath) {
-		shimTtsConfigSetVitsLexicon(cfg, lexiconPath)
-	}
-	if dataDir := filepath.Join(modelDir, "espeak-ng-data"); dirExists(dataDir) {
-		shimTtsConfigSetVitsDataDir(cfg, dataDir)
-	}
-
-	shimTtsConfigSetVitsNoiseScale(cfg, findOptionFloat(opts, optionTtsNoiseScale, 0.667))
-	shimTtsConfigSetVitsNoiseScaleW(cfg, findOptionFloat(opts, optionTtsNoiseScaleW, 0.8))
-	shimTtsConfigSetVitsLengthScale(cfg, findOptionFloat(opts, optionTtsLengthScale, 1.0))
 
 	threads := int32(1)
 	if opts.Threads != 0 {
@@ -723,6 +732,80 @@ func (s *SherpaBackend) loadTTS(opts *pb.ModelOptions) error {
 	return nil
 }
 
+// kokoroVoicesFile is the speaker-style bank that ships with Kokoro models and
+// is absent from VITS/Piper voices; its presence is how loadTTS tells them apart.
+const kokoroVoicesFile = "voices.bin"
+
+// isKokoroModel reports whether modelDir holds a Kokoro model (a voices file
+// next to the ONNX) rather than a VITS/Piper single-speaker model.
+func isKokoroModel(modelDir string) bool {
+	return fileExists(filepath.Join(modelDir, kokoroVoicesFile))
+}
+
+// configureVitsTTS wires a VITS/Piper single-speaker model into cfg: the ONNX
+// plus the optional tokens, lexicon and espeak-ng-data found beside it.
+func (s *SherpaBackend) configureVitsTTS(cfg uintptr, opts *pb.ModelOptions, modelFile, modelDir string) {
+	shimTtsConfigSetVitsModel(cfg, modelFile)
+
+	if tokensPath := filepath.Join(modelDir, "tokens.txt"); fileExists(tokensPath) {
+		shimTtsConfigSetVitsTokens(cfg, tokensPath)
+	}
+	if lexiconPath := filepath.Join(modelDir, "lexicon.txt"); fileExists(lexiconPath) {
+		shimTtsConfigSetVitsLexicon(cfg, lexiconPath)
+	}
+	if dataDir := filepath.Join(modelDir, "espeak-ng-data"); dirExists(dataDir) {
+		shimTtsConfigSetVitsDataDir(cfg, dataDir)
+	}
+
+	shimTtsConfigSetVitsNoiseScale(cfg, findOptionFloat(opts, optionTtsNoiseScale, 0.667))
+	shimTtsConfigSetVitsNoiseScaleW(cfg, findOptionFloat(opts, optionTtsNoiseScaleW, 0.8))
+	shimTtsConfigSetVitsLengthScale(cfg, findOptionFloat(opts, optionTtsLengthScale, 1.0))
+}
+
+// configureKokoroTTS wires a Kokoro model into cfg: the ONNX, its voices bank,
+// tokens, and the optional espeak-ng-data / jieba dict / lexicon assets the
+// multi-lingual packs ship. A language hint comes from the `language=` option.
+func (s *SherpaBackend) configureKokoroTTS(cfg uintptr, opts *pb.ModelOptions, modelFile, modelDir string) {
+	shimTtsConfigSetKokoroModel(cfg, modelFile)
+	shimTtsConfigSetKokoroVoices(cfg, filepath.Join(modelDir, kokoroVoicesFile))
+
+	if tokensPath := filepath.Join(modelDir, "tokens.txt"); fileExists(tokensPath) {
+		shimTtsConfigSetKokoroTokens(cfg, tokensPath)
+	}
+	if dataDir := filepath.Join(modelDir, "espeak-ng-data"); dirExists(dataDir) {
+		shimTtsConfigSetKokoroDataDir(cfg, dataDir)
+	}
+	if dictDir := filepath.Join(modelDir, "dict"); dirExists(dictDir) {
+		shimTtsConfigSetKokoroDictDir(cfg, dictDir)
+	}
+
+	// Multi-lingual Kokoro ships per-language lexicons; the C API takes them as
+	// a single comma-separated list. US and GB English overlap almost entirely,
+	// so pass only one (US preferred) to avoid tens of thousands of "duplicated
+	// word" warnings at load; non-English lexicons (e.g. zh) are additive.
+	var lexicons []string
+	addLexicon := func(name string) {
+		if p := filepath.Join(modelDir, name); fileExists(p) {
+			lexicons = append(lexicons, p)
+		}
+	}
+	if fileExists(filepath.Join(modelDir, "lexicon-us-en.txt")) {
+		addLexicon("lexicon-us-en.txt")
+	} else {
+		addLexicon("lexicon-gb-en.txt")
+	}
+	addLexicon("lexicon-zh.txt")
+	addLexicon("lexicon.txt")
+	if len(lexicons) > 0 {
+		shimTtsConfigSetKokoroLexicon(cfg, strings.Join(lexicons, ","))
+	}
+
+	if lang := findOptionValue(opts, optionLanguage, ""); lang != "" {
+		shimTtsConfigSetKokoroLang(cfg, lang)
+	}
+	shimTtsConfigSetKokoroLengthScale(cfg, findOptionFloat(opts, optionTtsLengthScale, 1.0))
+}
+
 func fileExists(p string) bool {
 	info, err := os.Stat(p)
 	return err == nil && !info.IsDir()
@@ -1252,7 +1335,7 @@ type ttsStreamState struct {
 var (
 	ttsStates      sync.Map // uint64 → *ttsStreamState
 	ttsNextID      atomic.Uint64
-	ttsCallbackPtr uintptr  // purego.NewCallback return; registered in loadSherpaLibs
+	ttsCallbackPtr uintptr // purego.NewCallback return; registered in loadSherpaLibs
 )
 
 // ttsStreamCallback is invoked by sherpa-onnx for each PCM chunk VITS

backend/go/sherpa-onnx/backend_test.go

@@ -124,6 +124,20 @@ var _ = Describe("Sherpa-ONNX", func() {
 			Entry("empty", "", false),
 			Entry("other", "other", false),
 		)
+
+		It("isKokoroModel detects a voices file beside the ONNX", func() {
+			dir, err := os.MkdirTemp("", "sherpa-kokoro-*")
+			Expect(err).NotTo(HaveOccurred())
+			defer func() { _ = os.RemoveAll(dir) }()
+
+			// A bare VITS/Piper directory (ONNX only) is not Kokoro.
+			Expect(os.WriteFile(filepath.Join(dir, "model.onnx"), []byte("x"), 0o600)).To(Succeed())
+			Expect(isKokoroModel(dir)).To(BeFalse())
+
+			// Adding the Kokoro voices bank flips detection on.
+			Expect(os.WriteFile(filepath.Join(dir, kokoroVoicesFile), []byte("x"), 0o600)).To(Succeed())
+			Expect(isKokoroModel(dir)).To(BeTrue())
+		})
 	})
 
 	Context("option parsing", func() {

backend/go/sherpa-onnx/csrc/shim.c

@@ -79,6 +79,13 @@ void sherpa_shim_tts_config_free(void *h) {
     free((char *)c->model.vits.tokens);
     free((char *)c->model.vits.lexicon);
     free((char *)c->model.vits.data_dir);
+    free((char *)c->model.kokoro.model);
+    free((char *)c->model.kokoro.voices);
+    free((char *)c->model.kokoro.tokens);
+    free((char *)c->model.kokoro.data_dir);
+    free((char *)c->model.kokoro.dict_dir);
+    free((char *)c->model.kokoro.lexicon);
+    free((char *)c->model.kokoro.lang);
     free((char *)c->model.provider);
     free(c);
 }
@@ -117,6 +124,34 @@ void sherpa_shim_tts_config_set_max_num_sentences(void *h, int32_t v) {
     ((SherpaOnnxOfflineTtsConfig *)h)->max_num_sentences = v;
 }
 
+// Kokoro multi-speaker / multi-lingual TTS. Distinct ONNX + a voices style
+// file (voices.bin) instead of VITS' single-speaker graph; espeak-ng-data,
+// lexicon and a language hint are optional refinements.
+void sherpa_shim_tts_config_set_kokoro_model(void *h, const char *v) {
+    shim_set_str(&((SherpaOnnxOfflineTtsConfig *)h)->model.kokoro.model, v);
+}
+void sherpa_shim_tts_config_set_kokoro_voices(void *h, const char *v) {
+    shim_set_str(&((SherpaOnnxOfflineTtsConfig *)h)->model.kokoro.voices, v);
+}
+void sherpa_shim_tts_config_set_kokoro_tokens(void *h, const char *v) {
+    shim_set_str(&((SherpaOnnxOfflineTtsConfig *)h)->model.kokoro.tokens, v);
+}
+void sherpa_shim_tts_config_set_kokoro_data_dir(void *h, const char *v) {
+    shim_set_str(&((SherpaOnnxOfflineTtsConfig *)h)->model.kokoro.data_dir, v);
+}
+void sherpa_shim_tts_config_set_kokoro_dict_dir(void *h, const char *v) {
+    shim_set_str(&((SherpaOnnxOfflineTtsConfig *)h)->model.kokoro.dict_dir, v);
+}
+void sherpa_shim_tts_config_set_kokoro_lexicon(void *h, const char *v) {
+    shim_set_str(&((SherpaOnnxOfflineTtsConfig *)h)->model.kokoro.lexicon, v);
+}
+void sherpa_shim_tts_config_set_kokoro_lang(void *h, const char *v) {
+    shim_set_str(&((SherpaOnnxOfflineTtsConfig *)h)->model.kokoro.lang, v);
+}
+void sherpa_shim_tts_config_set_kokoro_length_scale(void *h, float v) {
+    ((SherpaOnnxOfflineTtsConfig *)h)->model.kokoro.length_scale = v;
+}
+
 void *sherpa_shim_create_offline_tts(void *h) {
     return (void *)SherpaOnnxCreateOfflineTts(
         (const SherpaOnnxOfflineTtsConfig *)h);

backend/go/sherpa-onnx/csrc/shim.h

@@ -37,7 +37,7 @@ void  sherpa_shim_vad_config_set_provider(void *cfg, const char *v);
 void  sherpa_shim_vad_config_set_debug(void *cfg, int32_t v);
 void *sherpa_shim_create_vad(void *cfg, float buffer_size_seconds);
 
-// --- Offline TTS config (VITS path — the only TTS family the backend uses) ---
+// --- Offline TTS config (VITS/Piper and Kokoro model families) ---
 void *sherpa_shim_tts_config_new(void);
 void  sherpa_shim_tts_config_free(void *cfg);
 void  sherpa_shim_tts_config_set_vits_model(void *cfg, const char *v);
@@ -51,6 +51,14 @@ void  sherpa_shim_tts_config_set_num_threads(void *cfg, int32_t v);
 void  sherpa_shim_tts_config_set_debug(void *cfg, int32_t v);
 void  sherpa_shim_tts_config_set_provider(void *cfg, const char *v);
 void  sherpa_shim_tts_config_set_max_num_sentences(void *cfg, int32_t v);
+void  sherpa_shim_tts_config_set_kokoro_model(void *cfg, const char *v);
+void  sherpa_shim_tts_config_set_kokoro_voices(void *cfg, const char *v);
+void  sherpa_shim_tts_config_set_kokoro_tokens(void *cfg, const char *v);
+void  sherpa_shim_tts_config_set_kokoro_data_dir(void *cfg, const char *v);
+void  sherpa_shim_tts_config_set_kokoro_dict_dir(void *cfg, const char *v);
+void  sherpa_shim_tts_config_set_kokoro_lexicon(void *cfg, const char *v);
+void  sherpa_shim_tts_config_set_kokoro_lang(void *cfg, const char *v);
+void  sherpa_shim_tts_config_set_kokoro_length_scale(void *cfg, float v);
 void *sherpa_shim_create_offline_tts(void *cfg);
 
 // --- Offline recognizer config (Whisper / Paraformer / SenseVoice / Omnilingual) ---

backend/go/stablediffusion-ggml/Makefile

@@ -8,10 +8,16 @@ JOBS?=$(shell nproc --ignore=1)
 
 # stablediffusion.cpp (ggml)
 STABLEDIFFUSION_GGML_REPO?=https://github.com/leejet/stable-diffusion.cpp
-STABLEDIFFUSION_GGML_VERSION?=19bdfe22d255d5b4dff39d449318b9bc5ea2317f
+STABLEDIFFUSION_GGML_VERSION?=7f0e728b7d42f2490dfa5dd9539082d904f2f6b2
 
 CMAKE_ARGS+=-DGGML_MAX_NAME=128
 
+# Enable the ggml RPC backend so generation can be sharded across remote
+# rpc-server workers (the same backend-agnostic ggml rpc-server used by the
+# llama.cpp backend). Servers are selected via the `rpc_servers` option or the
+# LLAMACPP_GRPC_SERVERS env var (populated automatically in p2p worker mode).
+CMAKE_ARGS+=-DSD_RPC=ON
+
 ifeq ($(NATIVE),false)
 	CMAKE_ARGS+=-DGGML_NATIVE=OFF
 endif

backend/go/stablediffusion-ggml/cpp/gosd.cpp

@@ -391,10 +391,18 @@ int load_model(const char *model, char *model_path, char* options[], int threads
     const char *control_net_path = "";
     const char *embedding_dir = "";
     const char *photo_maker_path = "";
+    const char *pulid_weights_path = "";
     const char *tensor_type_rules = "";
     char *lora_dir = model_path;
 
-    bool vae_decode_only = true;
+    // Upstream backend/parameter placement specs (see docs/.../stablediffusion).
+    // Empty means "leave at upstream default" (nullptr).
+    const char *backend_arg = "";
+    const char *params_backend_arg = "";
+    const char *rpc_servers_arg = "";
+    const char *max_vram_arg = "";
+    bool stream_layers = false;
+
     int n_threads = threads;
     enum sd_type_t wtype = SD_TYPE_COUNT;
     enum rng_type_t rng_type = CUDA_RNG;
@@ -418,7 +426,9 @@ int load_model(const char *model, char *model_path, char* options[], int threads
     // If options is not NULL, parse options
     for (int i = 0; options[i] != NULL; i++) {
         const char *optname = strtok(options[i], ":");
-        const char *optval = strtok(NULL, ":");
+        // Take everything after the first ':' as the value so values may
+        // themselves contain colons (e.g. rpc_servers host:port lists).
+        const char *optval = strtok(NULL, "");
         if (optval == NULL) {
             optval = "true";
         }
@@ -490,9 +500,21 @@ int load_model(const char *model, char *model_path, char* options[], int threads
             }
         }
         if (!strcmp(optname, "photo_maker_path")) photo_maker_path = strdup(optval);
+        if (!strcmp(optname, "pulid_weights_path")) pulid_weights_path = strdup(optval);
         if (!strcmp(optname, "tensor_type_rules")) tensor_type_rules = strdup(optval);
 
-        if (!strcmp(optname, "vae_decode_only")) vae_decode_only = (strcmp(optval, "true") == 0 || strcmp(optval, "1") == 0);
+        // Backend / parameter placement specs (see prepare_backend_assignments
+        // in the upstream CLI). These compose with the legacy keep_*_on_cpu /
+        // offload_params_to_cpu booleans below.
+        if (!strcmp(optname, "backend")) backend_arg = strdup(optval);
+        if (!strcmp(optname, "params_backend")) params_backend_arg = strdup(optval);
+        if (!strcmp(optname, "rpc_servers")) rpc_servers_arg = strdup(optval);
+        if (!strcmp(optname, "max_vram")) max_vram_arg = strdup(optval);
+        if (!strcmp(optname, "stream_layers")) stream_layers = (strcmp(optval, "true") == 0 || strcmp(optval, "1") == 0);
+
+        // vae_decode_only is still accepted for backwards compatibility with
+        // existing gallery configs, but upstream dropped the option (the model
+        // now decides), so it is parsed and ignored.
         if (!strcmp(optname, "offload_params_to_cpu")) offload_params_to_cpu = (strcmp(optval, "true") == 0 || strcmp(optval, "1") == 0);
         if (!strcmp(optname, "keep_clip_on_cpu")) keep_clip_on_cpu = (strcmp(optval, "true") == 0 || strcmp(optval, "1") == 0);
         if (!strcmp(optname, "keep_control_net_on_cpu")) keep_control_net_on_cpu = (strcmp(optval, "true") == 0 || strcmp(optval, "1") == 0);
@@ -591,20 +613,48 @@ int load_model(const char *model, char *model_path, char* options[], int threads
     ctx_params.embeddings = embedding_vec.empty() ? NULL : embedding_vec.data();
     ctx_params.embedding_count = static_cast<uint32_t>(embedding_vec.size());
     ctx_params.photo_maker_path = photo_maker_path;
+    if (strlen(pulid_weights_path) > 0) ctx_params.pulid_weights_path = pulid_weights_path;
     ctx_params.tensor_type_rules = tensor_type_rules;
-    ctx_params.vae_decode_only = vae_decode_only;
-    // XXX: Setting to true causes a segfault on the second run
-    ctx_params.free_params_immediately = false;
     ctx_params.n_threads = n_threads;
     ctx_params.rng_type = rng_type;
-    ctx_params.keep_clip_on_cpu = keep_clip_on_cpu;
     if (wtype != SD_TYPE_COUNT) ctx_params.wtype = wtype;
     if (sampler_rng_type != RNG_TYPE_COUNT) ctx_params.sampler_rng_type = sampler_rng_type;
     if (prediction != PREDICTION_COUNT) ctx_params.prediction = prediction;
     if (lora_apply_mode != LORA_APPLY_MODE_COUNT) ctx_params.lora_apply_mode = lora_apply_mode;
-    ctx_params.offload_params_to_cpu = offload_params_to_cpu;
-    ctx_params.keep_control_net_on_cpu = keep_control_net_on_cpu;
-    ctx_params.keep_vae_on_cpu = keep_vae_on_cpu;
+    // Backend / parameter placement specs. Upstream replaced the boolean
+    // CPU-offload knobs (offload_params_to_cpu, keep_clip_on_cpu, keep_vae_on_cpu,
+    // keep_control_net_on_cpu) with these specs. Seed from the explicit
+    // backend/params_backend options, then prepend the legacy boolean-derived
+    // assignments, mirroring prepare_backend_assignments() in the upstream CLI.
+    // These strings must outlive new_sd_ctx() below.
+    std::string backend_spec = backend_arg;
+    std::string params_backend_spec = params_backend_arg;
+    auto prepend_spec = [](std::string& spec, const char* assignment) {
+        spec = spec.empty() ? std::string(assignment) : std::string(assignment) + "," + spec;
+    };
+    if (offload_params_to_cpu) prepend_spec(params_backend_spec, "*=cpu");
+    if (keep_clip_on_cpu) prepend_spec(backend_spec, "te=cpu");
+    if (keep_vae_on_cpu) prepend_spec(backend_spec, "vae=cpu");
+    if (keep_control_net_on_cpu) prepend_spec(backend_spec, "controlnet=cpu");
+    if (!backend_spec.empty()) ctx_params.backend = backend_spec.c_str();
+    if (!params_backend_spec.empty()) ctx_params.params_backend = params_backend_spec.c_str();
+    // RPC servers: prefer the explicit option, otherwise fall back to the
+    // LLAMACPP_GRPC_SERVERS env var. LocalAI's p2p worker mode populates that
+    // var with discovered ggml rpc-server workers (shared with the llama.cpp
+    // backend), so distributed image generation works with no extra config.
+    if (strlen(rpc_servers_arg) > 0) {
+        ctx_params.rpc_servers = rpc_servers_arg;
+    } else {
+        const char* env_rpc_servers = std::getenv("LLAMACPP_GRPC_SERVERS");
+        if (env_rpc_servers != NULL && strlen(env_rpc_servers) > 0) {
+            ctx_params.rpc_servers = env_rpc_servers;
+        }
+    }
+    // max_vram: GiB budget or per-backend spec for graph-cut segmented param
+    // offload ("0" = disabled, "-1" = auto). stream_layers only has effect when
+    // max_vram is set.
+    if (strlen(max_vram_arg) > 0) ctx_params.max_vram = max_vram_arg;
+    ctx_params.stream_layers = stream_layers;
     ctx_params.diffusion_flash_attn = diffusion_flash_attn;
     ctx_params.tae_preview_only = tae_preview_only;
     ctx_params.diffusion_conv_direct = diffusion_conv_direct;

backend/go/supertonic/.gitignore

@@ -0,0 +1,4 @@
+/supertonic
+/sources/
+/backend-assets/
+/package/

backend/go/supertonic/Makefile

@@ -0,0 +1,62 @@
+CURRENT_DIR=$(abspath ./)
+GOCMD=go
+
+ONNX_VERSION?=1.24.4
+ONNX_ARCH?=x64
+ONNX_OS?=linux
+
+ifneq (,$(findstring aarch64,$(shell uname -m)))
+	ONNX_ARCH=aarch64
+endif
+
+ifeq ($(OS),Darwin)
+	ONNX_OS=osx
+	ifneq (,$(findstring arm64,$(shell uname -m)))
+		ONNX_ARCH=arm64
+	else
+		ONNX_ARCH=x86_64
+	endif
+endif
+
+# CUDA 12 ships as -gpu, CUDA 13 as -gpu_cuda13 (underscore). CPU has no suffix.
+ifeq ($(BUILD_TYPE),cublas)
+	ONNX_PROVIDER=cuda
+	ifeq ($(CUDA_MAJOR_VERSION),13)
+		ONNX_VARIANT=-gpu_cuda13
+	else
+		ONNX_VARIANT=-gpu
+	endif
+else
+	ONNX_VARIANT=
+	ONNX_PROVIDER=cpu
+endif
+
+sources/onnxruntime:
+	mkdir -p sources/onnxruntime
+	curl -L https://github.com/microsoft/onnxruntime/releases/download/v$(ONNX_VERSION)/onnxruntime-$(ONNX_OS)-$(ONNX_ARCH)$(ONNX_VARIANT)-$(ONNX_VERSION).tgz \
+	  -o sources/onnxruntime/onnxruntime.tgz
+	cd sources/onnxruntime && tar -xf onnxruntime.tgz --strip-components=1 && rm onnxruntime.tgz
+
+backend-assets/lib: sources/onnxruntime
+	mkdir -p backend-assets/lib
+	cp -rfLv sources/onnxruntime/lib/* backend-assets/lib/
+
+supertonic: backend-assets/lib
+	CGO_ENABLED=1 $(GOCMD) build \
+	  -ldflags "$(LD_FLAGS) -X main.onnxProvider=$(ONNX_PROVIDER)" \
+	  -tags "$(GO_TAGS)" -o supertonic ./
+
+package:
+	bash package.sh
+
+build: supertonic package
+
+# Tests need only the Go toolchain (gcc); yalue dlopens onnxruntime at
+# runtime, so no tarball download is required to compile or run unit specs.
+test:
+	CGO_ENABLED=1 $(GOCMD) test -v -timeout 120s ./...
+
+clean:
+	rm -rf supertonic sources/ backend-assets/ package/
+
+.PHONY: build package clean test

backend/go/supertonic/backend.go

@@ -0,0 +1,307 @@
+package main
+
+import (
+	"bytes"
+	"encoding/binary"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"sync"
+
+	laudio "github.com/mudler/LocalAI/pkg/audio"
+	"github.com/mudler/LocalAI/pkg/grpc/base"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+)
+
+// onnxProvider is set via -ldflags "-X main.onnxProvider=cuda" by the
+// CUDA build (later phase). Defaults to CPU.
+var onnxProvider = "cpu"
+
+// Per-model generation defaults, overridable via ModelOptions.Options:
+//
+//	supertonic.steps=<int>          denoising steps (quality), default 8
+//	supertonic.speed=<float>        speech rate, default 1.05
+//	supertonic.silence=<float>      inter-chunk silence seconds, default 0.3
+//	supertonic.default_voice=<name> voice-style used when request omits voice
+//	supertonic.default_lang=<lang>  language tag used when request omits it
+const (
+	optionSteps        = "supertonic.steps="
+	optionSpeed        = "supertonic.speed="
+	optionSilence      = "supertonic.silence="
+	optionDefaultVoice = "supertonic.default_voice="
+	optionDefaultLang  = "supertonic.default_lang="
+)
+
+type SupertonicBackend struct {
+	base.SingleThread
+
+	tts          *TextToSpeech
+	cfg          Config
+	modelDir     string
+	voicesDir    string
+	defaultVoice string
+	defaultLang  string
+	steps        int
+	speed        float32
+	silence      float32
+
+	styleMu sync.Mutex
+	styles  map[string]*Style // voice name -> loaded style cache
+}
+
+func (s *SupertonicBackend) Load(opts *pb.ModelOptions) error {
+	modelDir, err := resolveModelDir(opts.ModelFile)
+	if err != nil {
+		return err
+	}
+	s.modelDir = modelDir
+	s.voicesDir = resolveVoicesDir(modelDir)
+
+	cfg, err := LoadCfgs(modelDir)
+	if err != nil {
+		return fmt.Errorf("loading tts.json from %s: %w", modelDir, err)
+	}
+	s.cfg = cfg
+
+	// onnxProvider is "cpu" for the CPU build; the CUDA build sets it to
+	// "cuda" via -ldflags. Upstream LoadTextToSpeech still errors on GPU
+	// until the CUDA phase wires the execution provider.
+	tts, err := LoadTextToSpeech(modelDir, onnxProvider == "cuda", cfg)
+	if err != nil {
+		return fmt.Errorf("loading supertonic models from %s: %w", modelDir, err)
+	}
+	s.tts = tts
+
+	s.steps = int(findOptionInt(opts, optionSteps, 8))
+	s.speed = findOptionFloat(opts, optionSpeed, 1.05)
+	s.silence = findOptionFloat(opts, optionSilence, 0.3)
+	s.defaultVoice = findOptionValue(opts, optionDefaultVoice, "")
+	s.defaultLang = findOptionValue(opts, optionDefaultLang, "na")
+	s.styles = map[string]*Style{}
+	return nil
+}
+
+func (s *SupertonicBackend) TTS(req *pb.TTSRequest) error {
+	wav, sr, err := s.synthesize(req)
+	if err != nil {
+		return err
+	}
+	out := make([]float64, len(wav))
+	for i, v := range wav {
+		out[i] = float64(v)
+	}
+	if err := writeWavFile(req.Dst, out, sr); err != nil {
+		return fmt.Errorf("writing wav to %s: %w", req.Dst, err)
+	}
+	return nil
+}
+
+func (s *SupertonicBackend) TTSStream(req *pb.TTSRequest, results chan []byte) error {
+	defer close(results)
+
+	wav, sr, err := s.synthesize(req)
+	if err != nil {
+		return err
+	}
+
+	results <- streamingWAVHeader(uint32(sr))
+
+	const chunkSamples = 4096
+	for off := 0; off < len(wav); off += chunkSamples {
+		end := off + chunkSamples
+		if end > len(wav) {
+			end = len(wav)
+		}
+		results <- pcmFloatToInt16LE(wav[off:end])
+	}
+	return nil
+}
+
+// synthesize runs the full pipeline and returns the trimmed mono float32
+// PCM and its sample rate.
+func (s *SupertonicBackend) synthesize(req *pb.TTSRequest) ([]float32, int, error) {
+	if s.tts == nil {
+		return nil, 0, fmt.Errorf("supertonic model not loaded")
+	}
+	if strings.TrimSpace(req.Text) == "" {
+		return nil, 0, fmt.Errorf("empty text")
+	}
+
+	style, err := s.loadStyle(s.voiceName(req.Voice))
+	if err != nil {
+		return nil, 0, err
+	}
+
+	lang := s.resolveLang("")
+	if req.Language != nil {
+		lang = s.resolveLang(*req.Language)
+	}
+
+	wav, dur, err := s.tts.Call(req.Text, lang, style, s.steps, s.speed, s.silence)
+	if err != nil {
+		return nil, 0, err
+	}
+
+	sr := s.tts.SampleRate
+	// Call returns concatenated audio; trim to the reported duration.
+	wavLen := int(float32(sr) * dur)
+	if wavLen < 0 {
+		wavLen = 0
+	}
+	if wavLen > len(wav) {
+		wavLen = len(wav)
+	}
+	return wav[:wavLen], sr, nil
+}
+
+// voiceName picks the request voice, falling back to the model default.
+func (s *SupertonicBackend) voiceName(reqVoice string) string {
+	v := strings.TrimSpace(reqVoice)
+	if v == "" {
+		return s.defaultVoice
+	}
+	return v
+}
+
+// resolveLang validates against AvailableLangs, falling back to the model
+// default (then "na").
+func (s *SupertonicBackend) resolveLang(reqLang string) string {
+	l := strings.TrimSpace(reqLang)
+	if l != "" && isValidLang(l) {
+		return l
+	}
+	if s.defaultLang != "" && isValidLang(s.defaultLang) {
+		return s.defaultLang
+	}
+	return "na"
+}
+
+// loadStyle resolves and caches a voice-style. An empty name with no model
+// default is an error (supertonic requires a style embedding).
+func (s *SupertonicBackend) loadStyle(name string) (*Style, error) {
+	if name == "" {
+		return nil, fmt.Errorf("no voice specified and no supertonic.default_voice set")
+	}
+	s.styleMu.Lock()
+	defer s.styleMu.Unlock()
+	if st, ok := s.styles[name]; ok {
+		return st, nil
+	}
+	path := s.voiceStylePath(name)
+	st, err := LoadVoiceStyle([]string{path}, false)
+	if err != nil {
+		return nil, fmt.Errorf("loading voice style %q (%s): %w", name, path, err)
+	}
+	s.styles[name] = st
+	return st, nil
+}
+
+// voiceStylePath maps a voice name to a JSON path. Absolute paths are honored;
+// names containing a separator resolve under modelDir; bare names resolve under
+// the resolved voicesDir (see resolveVoicesDir).
+func (s *SupertonicBackend) voiceStylePath(name string) string {
+	if !strings.HasSuffix(name, ".json") {
+		name += ".json"
+	}
+	if filepath.IsAbs(name) {
+		return name
+	}
+	if strings.ContainsRune(name, filepath.Separator) {
+		return filepath.Join(s.modelDir, name)
+	}
+	return filepath.Join(s.voicesDir, name)
+}
+
+// resolveVoicesDir locates the voice_styles directory. The HF model layout
+// puts the ONNX files in an onnx/ subdir with voice_styles/ as its sibling,
+// so check modelDir/voice_styles first, then the parent's voice_styles.
+func resolveVoicesDir(modelDir string) string {
+	candidates := []string{
+		filepath.Join(modelDir, "voice_styles"),
+		filepath.Join(filepath.Dir(modelDir), "voice_styles"),
+	}
+	for _, c := range candidates {
+		if info, err := os.Stat(c); err == nil && info.IsDir() {
+			return c
+		}
+	}
+	return candidates[0]
+}
+
+// resolveModelDir accepts either a directory (used as-is) or a file (its
+// parent dir is used).
+func resolveModelDir(modelFile string) (string, error) {
+	if modelFile == "" {
+		return "", fmt.Errorf("empty model path")
+	}
+	info, err := os.Stat(modelFile)
+	if err != nil {
+		return "", fmt.Errorf("stat model path %s: %w", modelFile, err)
+	}
+	if info.IsDir() {
+		return modelFile, nil
+	}
+	return filepath.Dir(modelFile), nil
+}
+
+// ---- option helpers (mirrors backend/go/sherpa-onnx/backend.go) ----
+
+func findOptionValue(opts *pb.ModelOptions, prefix, def string) string {
+	for _, o := range opts.Options {
+		if strings.HasPrefix(o, prefix) {
+			return strings.TrimPrefix(o, prefix)
+		}
+	}
+	return def
+}
+
+func findOptionFloat(opts *pb.ModelOptions, prefix string, def float32) float32 {
+	raw := findOptionValue(opts, prefix, "")
+	if raw == "" {
+		return def
+	}
+	v, err := strconv.ParseFloat(raw, 32)
+	if err != nil {
+		return def
+	}
+	return float32(v)
+}
+
+func findOptionInt(opts *pb.ModelOptions, prefix string, def int32) int32 {
+	raw := findOptionValue(opts, prefix, "")
+	if raw == "" {
+		return def
+	}
+	v, err := strconv.ParseInt(raw, 10, 32)
+	if err != nil {
+		return def
+	}
+	return int32(v)
+}
+
+// ---- PCM helpers ----
+
+func pcmFloatToInt16LE(samples []float32) []byte {
+	buf := make([]byte, len(samples)*2)
+	for i, f := range samples {
+		v := int32(f * 32767)
+		if v > 32767 {
+			v = 32767
+		} else if v < -32768 {
+			v = -32768
+		}
+		binary.LittleEndian.PutUint16(buf[2*i:], uint16(int16(v)))
+	}
+	return buf
+}
+
+func streamingWAVHeader(sampleRate uint32) []byte {
+	const streamingSize = 0xFFFFFFFF
+	h := laudio.NewWAVHeaderWithRate(streamingSize, sampleRate)
+	h.ChunkSize = streamingSize
+	var buf bytes.Buffer
+	_ = h.Write(&buf)
+	return buf.Bytes()
+}

backend/go/supertonic/backend_test.go

@@ -0,0 +1,86 @@
+package main
+
+import (
+	"os"
+	"path/filepath"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+)
+
+var _ = Describe("voiceStylePath", func() {
+	s := &SupertonicBackend{modelDir: "/models/st/onnx", voicesDir: "/models/st/voice_styles"}
+
+	It("resolves a bare name under the resolved voicesDir", func() {
+		Expect(s.voiceStylePath("M1")).To(Equal(filepath.Join("/models/st/voice_styles", "M1.json")))
+	})
+	It("keeps an explicit .json suffix", func() {
+		Expect(s.voiceStylePath("M1.json")).To(Equal(filepath.Join("/models/st/voice_styles", "M1.json")))
+	})
+	It("honors absolute paths", func() {
+		Expect(s.voiceStylePath("/abs/v.json")).To(Equal("/abs/v.json"))
+	})
+})
+
+var _ = Describe("resolveVoicesDir", func() {
+	It("prefers voice_styles under modelDir", func() {
+		dir := GinkgoT().TempDir()
+		Expect(os.MkdirAll(filepath.Join(dir, "voice_styles"), 0o755)).To(Succeed())
+		Expect(resolveVoicesDir(dir)).To(Equal(filepath.Join(dir, "voice_styles")))
+	})
+	It("falls back to the sibling voice_styles next to an onnx subdir", func() {
+		root := GinkgoT().TempDir()
+		Expect(os.MkdirAll(filepath.Join(root, "voice_styles"), 0o755)).To(Succeed())
+		Expect(os.MkdirAll(filepath.Join(root, "onnx"), 0o755)).To(Succeed())
+		Expect(resolveVoicesDir(filepath.Join(root, "onnx"))).To(Equal(filepath.Join(root, "voice_styles")))
+	})
+})
+
+var _ = Describe("resolveLang", func() {
+	It("accepts a valid request language", func() {
+		s := &SupertonicBackend{defaultLang: "na"}
+		Expect(s.resolveLang("ko")).To(Equal("ko"))
+	})
+	It("falls back to the model default for an invalid language", func() {
+		s := &SupertonicBackend{defaultLang: "en"}
+		Expect(s.resolveLang("zz")).To(Equal("en"))
+	})
+	It("falls back to na when nothing is valid", func() {
+		s := &SupertonicBackend{defaultLang: ""}
+		Expect(s.resolveLang("")).To(Equal("na"))
+	})
+})
+
+var _ = Describe("pcmFloatToInt16LE", func() {
+	It("clamps and encodes little-endian", func() {
+		out := pcmFloatToInt16LE([]float32{0, 1.0, -1.0, 2.0})
+		Expect(out).To(HaveLen(8))
+		Expect(out[0:2]).To(Equal([]byte{0x00, 0x00})) // 0
+		Expect(out[2:4]).To(Equal([]byte{0xff, 0x7f})) // 32767
+		Expect(out[6:8]).To(Equal([]byte{0xff, 0x7f})) // clamp 2.0 -> 32767
+	})
+})
+
+var _ = Describe("end-to-end synthesis", Ordered, func() {
+	var modelDir string
+	BeforeAll(func() {
+		modelDir = os.Getenv("SUPERTONIC_MODEL_PATH")
+		if modelDir == "" {
+			Skip("set SUPERTONIC_MODEL_PATH to a supertonic model dir to run")
+		}
+		Expect(InitializeONNXRuntime()).To(Succeed())
+	})
+
+	It("synthesizes a wav file", func() {
+		b := &SupertonicBackend{}
+		Expect(b.Load(&pb.ModelOptions{ModelFile: modelDir, Options: []string{"supertonic.default_voice=F1"}})).To(Succeed())
+		dst := filepath.Join(GinkgoT().TempDir(), "out.wav")
+		lang := "en"
+		Expect(b.TTS(&pb.TTSRequest{Text: "Hello from LocalAI.", Dst: dst, Language: &lang})).To(Succeed())
+		info, err := os.Stat(dst)
+		Expect(err).ToNot(HaveOccurred())
+		Expect(info.Size()).To(BeNumerically(">", 44)) // header + PCM
+	})
+})

backend/go/supertonic/main.go

@@ -0,0 +1,27 @@
+package main
+
+// Started internally by LocalAI; a server is allocated per model.
+
+import (
+	"flag"
+
+	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	ort "github.com/yalue/onnxruntime_go"
+)
+
+var addr = flag.String("addr", "localhost:50051", "the address to connect to")
+
+func main() {
+	flag.Parse()
+
+	// InitializeONNXRuntime reads ONNXRUNTIME_LIB_PATH (set by run.sh) and
+	// dlopens libonnxruntime before any session is created in Load().
+	if err := InitializeONNXRuntime(); err != nil {
+		panic(err)
+	}
+	defer func() { _ = ort.DestroyEnvironment() }()
+
+	if err := grpc.StartServer(*addr, &SupertonicBackend{}); err != nil {
+		panic(err)
+	}
+}

backend/go/supertonic/main_suite_test.go

@@ -1,4 +1,4 @@
-package ssewire
+package main
 
 import (
 	"testing"
@@ -7,7 +7,7 @@ import (
 	. "github.com/onsi/gomega"
 )
 
-func TestSsewire(t *testing.T) {
+func TestSupertonic(t *testing.T) {
 	RegisterFailHandler(Fail)
-	RunSpecs(t, "ssewire test suite")
+	RunSpecs(t, "Supertonic backend test suite")
 }

backend/go/supertonic/package.sh

@@ -0,0 +1,49 @@
+#!/bin/bash
+set -e
+
+CURDIR=$(dirname "$(realpath $0)")
+REPO_ROOT="${CURDIR}/../../.."
+
+mkdir -p $CURDIR/package/lib
+
+cp -avf $CURDIR/supertonic $CURDIR/package/
+cp -avf $CURDIR/run.sh $CURDIR/package/
+cp -rfLv $CURDIR/backend-assets/lib/* $CURDIR/package/lib/
+
+if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
+    echo "Detected x86_64 architecture, copying x86_64 libraries..."
+    cp -arfLv /lib64/ld-linux-x86-64.so.2 $CURDIR/package/lib/ld.so
+    cp -arfLv /lib/x86_64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
+    cp -arfLv /lib/x86_64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
+elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
+    echo "Detected ARM64 architecture, copying ARM64 libraries..."
+    cp -arfLv /lib/ld-linux-aarch64.so.1 $CURDIR/package/lib/ld.so
+    cp -arfLv /lib/aarch64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
+    cp -arfLv /lib/aarch64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
+else
+    echo "Error: Could not detect architecture"
+    exit 1
+fi
+
+GPU_LIB_SCRIPT="${REPO_ROOT}/scripts/build/package-gpu-libs.sh"
+if [ -f "$GPU_LIB_SCRIPT" ]; then
+    echo "Packaging GPU libraries for BUILD_TYPE=${BUILD_TYPE:-cpu}..."
+    source "$GPU_LIB_SCRIPT" "$CURDIR/package/lib"
+    package_gpu_libs
+fi
+
+echo "Packaging completed successfully"
+ls -liah $CURDIR/package/
+ls -liah $CURDIR/package/lib/

backend/go/supertonic/run.sh

@@ -0,0 +1,14 @@
+#!/bin/bash
+set -ex
+
+CURDIR=$(dirname "$(realpath $0)")
+
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
+export ONNXRUNTIME_LIB_PATH=$CURDIR/lib/libonnxruntime.so
+
+if [ -f $CURDIR/lib/ld.so ]; then
+	echo "Using lib/ld.so"
+	exec $CURDIR/lib/ld.so $CURDIR/supertonic "$@"
+fi
+
+exec $CURDIR/supertonic "$@"

backend/go/whisper/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # whisper.cpp version
 WHISPER_REPO?=https://github.com/ggml-org/whisper.cpp
-WHISPER_CPP_VERSION?=df7638d8229a243af8a4b5a8ae557e0d74e0a0ae
+WHISPER_CPP_VERSION?=86c40c3bd6fc86f1187fb751d111b49e0fc18e84
 SO_TARGET?=libgowhisper.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

backend/index.yaml

@@ -366,6 +366,218 @@
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-locate-anything-cpp"
     intel: "intel-sycl-f32-locate-anything-cpp"
     vulkan: "vulkan-locate-anything-cpp"
+- !!merge <<: *locateanything
+  name: "locate-anything-development"
+  capabilities:
+    default: "cpu-locate-anything-cpp-development"
+    nvidia: "cuda12-locate-anything-cpp-development"
+    nvidia-cuda-12: "cuda12-locate-anything-cpp-development"
+    nvidia-cuda-13: "cuda13-locate-anything-cpp-development"
+    nvidia-l4t: "nvidia-l4t-arm64-locate-anything-cpp-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-locate-anything-cpp-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-locate-anything-cpp-development"
+    intel: "intel-sycl-f32-locate-anything-cpp-development"
+    vulkan: "vulkan-locate-anything-cpp-development"
+- !!merge <<: *locateanything
+  name: "cpu-locate-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-cpu-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "cpu-locate-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-cpu-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "cuda12-locate-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "cuda12-locate-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "cuda13-locate-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "cuda13-locate-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "nvidia-l4t-arm64-locate-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-arm64-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "nvidia-l4t-arm64-locate-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-arm64-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "cuda13-nvidia-l4t-arm64-locate-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "cuda13-nvidia-l4t-arm64-locate-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "intel-sycl-f32-locate-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-sycl-f32-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "intel-sycl-f32-locate-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-sycl-f32-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "intel-sycl-f16-locate-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-sycl-f16-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "intel-sycl-f16-locate-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-sycl-f16-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "vulkan-locate-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-vulkan-locate-anything-cpp
+- !!merge <<: *locateanything
+  name: "vulkan-locate-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-locate-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-vulkan-locate-anything-cpp
+- &depthanything
+  name: "depth-anything"
+  alias: "depth-anything"
+  license: apache-2.0
+  description: |
+    Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
+    using GGML. Loads pre-built GGUF weights and, given an image, returns a
+    dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
+    (3x3). No Python at inference (purego, cgo-less).
+  urls:
+    - https://github.com/mudler/depth-anything.cpp
+    - https://huggingface.co/depth-anything/Depth-Anything-V3
+  tags:
+    - depth-estimation
+    - camera-pose
+    - depth-anything
+    - gpu
+    - cpu
+  capabilities:
+    default: "cpu-depth-anything-cpp"
+    nvidia: "cuda12-depth-anything-cpp"
+    nvidia-cuda-12: "cuda12-depth-anything-cpp"
+    nvidia-cuda-13: "cuda13-depth-anything-cpp"
+    nvidia-l4t: "nvidia-l4t-arm64-depth-anything-cpp"
+    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-depth-anything-cpp"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-depth-anything-cpp"
+    intel: "intel-sycl-f32-depth-anything-cpp"
+    vulkan: "vulkan-depth-anything-cpp"
+- !!merge <<: *depthanything
+  name: "depth-anything-development"
+  capabilities:
+    default: "cpu-depth-anything-cpp-development"
+    nvidia: "cuda12-depth-anything-cpp-development"
+    nvidia-cuda-12: "cuda12-depth-anything-cpp-development"
+    nvidia-cuda-13: "cuda13-depth-anything-cpp-development"
+    nvidia-l4t: "nvidia-l4t-arm64-depth-anything-cpp-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-depth-anything-cpp-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-depth-anything-cpp-development"
+    intel: "intel-sycl-f32-depth-anything-cpp-development"
+    vulkan: "vulkan-depth-anything-cpp-development"
+- !!merge <<: *depthanything
+  name: "cpu-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-cpu-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "cpu-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-cpu-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "cuda12-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "cuda12-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "cuda13-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "cuda13-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "nvidia-l4t-arm64-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-arm64-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "nvidia-l4t-arm64-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-arm64-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "cuda13-nvidia-l4t-arm64-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "cuda13-nvidia-l4t-arm64-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "intel-sycl-f32-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-sycl-f32-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "intel-sycl-f32-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-sycl-f32-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "intel-sycl-f16-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-sycl-f16-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "intel-sycl-f16-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-sycl-f16-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "vulkan-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-vulkan-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "vulkan-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-vulkan-depth-anything-cpp
 - &vllm
   name: "vllm"
   license: apache-2.0
@@ -455,12 +667,9 @@
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-vllm-omni"
 - &mlx
   name: "mlx"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx"
   icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
   urls:
     - https://github.com/ml-explore/mlx-lm
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-mlx
   license: MIT
   description: |
       Run LLMs with MLX
@@ -479,12 +688,9 @@
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-mlx"
 - &mlx-vlm
   name: "mlx-vlm"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-vlm"
   icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
   urls:
     - https://github.com/Blaizzy/mlx-vlm
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-mlx-vlm
   license: MIT
   description: |
       Run Vision-Language Models with MLX
@@ -505,12 +711,9 @@
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-mlx-vlm"
 - &mlx-audio
   name: "mlx-audio"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-audio"
   icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
   urls:
     - https://github.com/Blaizzy/mlx-audio
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-mlx-audio
   license: MIT
   description: |
       Run Audio Models with MLX
@@ -531,12 +734,9 @@
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-mlx-audio"
 - &mlx-distributed
   name: "mlx-distributed"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-distributed"
   icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4
   urls:
     - https://github.com/ml-explore/mlx-lm
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-mlx-distributed
   license: MIT
   description: |
       Run distributed LLM inference with MLX across multiple Apple Silicon Macs
@@ -632,7 +832,7 @@
     default: "cpu-diffusers"
     nvidia-cuda-13: "cuda13-diffusers"
     nvidia-cuda-12: "cuda12-diffusers"
-    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-diffusers"
+    nvidia-l4t-cuda-12: "nvidia-l4t-diffusers"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-diffusers"
 - &ace-step
   name: "ace-step"
@@ -688,14 +888,17 @@
 - &qwen3ttscpp
   name: "qwen3-tts-cpp"
   description: |
-    Qwen3-TTS C++ backend using GGML. Native C++ text-to-speech with voice cloning support.
-    Generates 24kHz mono audio from text with optional reference audio for voice cloning via ECAPA-TDNN speaker embeddings.
+    Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech
+    with streaming output, named speakers, voice design, and zero-shot voice
+    cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B
+    models in Q8_0 / Q4_K_M.
   urls:
-    - https://github.com/predict-woo/qwen3-tts.cpp
+    - https://github.com/ServeurpersoCom/qwentts.cpp
   tags:
     - text-to-speech
     - tts
     - voice-cloning
+    - streaming
   alias: "qwen3-tts-cpp"
   capabilities:
     default: "cpu-qwen3-tts-cpp"
@@ -709,6 +912,33 @@
     nvidia-l4t: "nvidia-l4t-arm64-qwen3-tts-cpp"
     nvidia-l4t-cuda-12: "nvidia-l4t-arm64-qwen3-tts-cpp"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-qwen3-tts-cpp"
+- &omnivoicecpp
+  name: "omnivoice-cpp"
+  description: |
+    OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning
+    (reference audio + transcript) and voice design (attribute keywords: gender,
+    age, pitch, style, volume, emotion). 24kHz mono output, 646 languages.
+    Supports streaming synthesis.
+  urls:
+    - https://github.com/ServeurpersoCom/omnivoice.cpp
+  tags:
+    - text-to-speech
+    - tts
+    - voice-cloning
+    - voice-design
+  alias: "omnivoice-cpp"
+  capabilities:
+    default: "cpu-omnivoice-cpp"
+    nvidia: "cuda12-omnivoice-cpp"
+    nvidia-cuda-13: "cuda13-omnivoice-cpp"
+    nvidia-cuda-12: "cuda12-omnivoice-cpp"
+    intel: "intel-sycl-f16-omnivoice-cpp"
+    metal: "metal-omnivoice-cpp"
+    amd: "rocm-omnivoice-cpp"
+    vulkan: "vulkan-omnivoice-cpp"
+    nvidia-l4t: "nvidia-l4t-arm64-omnivoice-cpp"
+    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-omnivoice-cpp"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-omnivoice-cpp"
 - &vibevoicecpp
   name: "vibevoice-cpp"
   description: |
@@ -769,6 +999,42 @@
     nvidia-l4t: "vulkan-localvqe"
     nvidia-l4t-cuda-12: "vulkan-localvqe"
     nvidia-l4t-cuda-13: "vulkan-localvqe"
+- &privacyfilter
+  name: "privacy-filter"
+  alias: "privacy-filter"
+  icon: https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/QPiv8pt4JNxr0FdGnpFef.png
+  description: |
+    Standalone GGML engine (privacy-filter.cpp) for the OpenMed privacy-filter
+    PII/NER token-classification model family. It runs the openai-privacy-filter
+    architecture (a gpt-oss-style sparse-MoE bidirectional token classifier) on
+    stock upstream GGML — no llama.cpp coupling and no Python — and serves the
+    TokenClassify RPC (constrained BIOES Viterbi decode into UTF-8 byte-offset
+    entity spans) used by LocalAI's NER PII redaction tier.
+  urls:
+    - https://github.com/localai-org/privacy-filter.cpp
+  tags:
+    - token-classification
+    - ner
+    - pii
+    - privacy
+    - CPU
+    - GPU
+  license: apache-2.0
+  # Builds: CPU (amd64+arm64 manifest), Vulkan (amd64) and CUDA 13 (amd64).
+  # Only a host that actually reports CUDA 13 gets the CUDA image (it bundles
+  # the CUDA 13 runtime and needs a recent driver); every other GPU — including
+  # NVIDIA without a CUDA-13 toolkit, AMD and Intel — routes to the Vulkan
+  # image, which only needs a Vulkan ICD. Everything else (incl. arm64/Jetson,
+  # where Vulkan/CUDA images are a future add) falls back to the CPU build,
+  # already fast for this ~50M-active-param model.
+  capabilities:
+    default: "cpu-privacy-filter"
+    nvidia: "vulkan-privacy-filter"
+    nvidia-cuda-12: "vulkan-privacy-filter"
+    nvidia-cuda-13: "cuda13-privacy-filter"
+    amd: "vulkan-privacy-filter"
+    intel: "vulkan-privacy-filter"
+    vulkan: "vulkan-privacy-filter"
 - &faster-whisper
   icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4
   description: |
@@ -854,7 +1120,7 @@
     metal: "metal-kokoro"
     nvidia-cuda-13: "cuda13-kokoro"
     nvidia-cuda-12: "cuda12-kokoro"
-    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-kokoro"
+    nvidia-l4t-cuda-12: "nvidia-l4t-kokoro"
 - &kokoros
   icon: https://avatars.githubusercontent.com/u/166769057?v=4
   description: |
@@ -897,7 +1163,6 @@
     intel: "intel-coqui"
     amd: "rocm-coqui"
     metal: "metal-coqui"
-    nvidia-cuda-13: "cuda13-coqui"
     nvidia-cuda-12: "cuda12-coqui"
   icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4
 - &outetts
@@ -1147,27 +1412,27 @@
   icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4
 - &piper
   name: "piper"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-piper"
   icon: https://github.com/OHF-Voice/piper1-gpl/raw/main/etc/logo.png
   urls:
     - https://github.com/rhasspy/piper
     - https://github.com/mudler/go-piper
-  mirrors:
-    - localai/localai-backends:latest-piper
   license: MIT
   description: |
      A fast, local neural text to speech system
   tags:
     - text-to-speech
     - TTS
+  capabilities:
+    default: "cpu-piper"
+    metal: "metal-piper"
 - &opus
   name: "opus"
   alias: "opus"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-opus"
+  capabilities:
+    default: "cpu-opus"
+    metal: "metal-opus"
   urls:
     - https://opus-codec.org/
-  mirrors:
-    - localai/localai-backends:latest-cpu-opus
   license: BSD-3-Clause
   description: |
     Opus audio codec backend for encoding and decoding audio.
@@ -1177,15 +1442,19 @@
     - opus
     - WebRTC
     - realtime
-    - CPU
+- !!merge <<: *opus
+  name: "opus-development"
+  capabilities:
+    default: "cpu-opus-development"
+    metal: "metal-opus-development"
 - &silero-vad
   name: "silero-vad"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-silero-vad"
   icon: https://user-images.githubusercontent.com/12515440/89997349-b3523080-dc94-11ea-9906-ca2e8bc50535.png
   urls:
     - https://github.com/snakers4/silero-vad
-  mirrors:
-    - localai/localai-backends:latest-cpu-silero-vad
+  capabilities:
+    default: "cpu-silero-vad"
+    metal: "metal-silero-vad"
   description: |
     Silero VAD: pre-trained enterprise-grade Voice Activity Detector.
     Silero VAD is a voice activity detection model that can be used to detect whether a given audio contains speech or not.
@@ -1196,9 +1465,6 @@
     - CPU
 - &local-store
   name: "local-store"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-local-store"
-  mirrors:
-    - localai/localai-backends:latest-cpu-local-store
   urls:
     - https://github.com/mudler/LocalAI
   description: |
@@ -1209,11 +1475,11 @@
     - open-source
     - CPU
   license: MIT
+  capabilities:
+    default: "cpu-local-store"
+    metal: "metal-local-store"
 - &kitten-tts
   name: "kitten-tts"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-kitten-tts"
-  mirrors:
-    - localai/localai-backends:latest-kitten-tts
   urls:
     - https://github.com/KittenML/KittenTTS
   description: |
@@ -1222,6 +1488,9 @@
     - text-to-speech
     - TTS
   license: apache-2.0
+  capabilities:
+    default: "cpu-kitten-tts"
+    metal: "metal-kitten-tts"
 - &neutts
   name: "neutts"
   urls:
@@ -1255,6 +1524,20 @@
     nvidia: "cuda12-sherpa-onnx"
     nvidia-cuda-12: "cuda12-sherpa-onnx"
     metal: "metal-sherpa-onnx"
+- &supertonic
+  name: "supertonic"
+  alias: "supertonic"
+  urls:
+    - https://github.com/supertone-inc/supertonic
+  description: |
+    Supertonic backend: lightning-fast, on-device multilingual text-to-speech via ONNX Runtime.
+    Runs Supertone's flow-matching TTS model (Supertone/supertonic-3), 44.1kHz output, 31 languages,
+    multiple preset voice styles. No espeak-ng dependency.
+  tags:
+    - text-to-speech
+    - TTS
+  capabilities:
+    default: "cpu-supertonic"
 - !!merge <<: *neutts
   name: "neutts-development"
   capabilities:
@@ -1347,25 +1630,89 @@
   mirrors:
     - localai/localai-backends:master-gpu-rocm-hipblas-neutts
 - !!merge <<: *mlx
-  name: "mlx-development"
+  name: "metal-mlx"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-mlx
+- !!merge <<: *mlx
+  name: "metal-mlx-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx"
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-mlx
+- !!merge <<: *mlx
+  name: "mlx-development"
+  capabilities:
+    default: "cpu-mlx-development"
+    nvidia: "cuda12-mlx-development"
+    metal: "metal-mlx-development"
+    nvidia-cuda-12: "cuda12-mlx-development"
+    nvidia-cuda-13: "cuda13-mlx-development"
+    nvidia-l4t: "nvidia-l4t-mlx-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-mlx-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-mlx-development"
 - !!merge <<: *mlx-vlm
-  name: "mlx-vlm-development"
+  name: "metal-mlx-vlm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-vlm"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-mlx-vlm
+- !!merge <<: *mlx-vlm
+  name: "metal-mlx-vlm-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx-vlm"
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-mlx-vlm
+- !!merge <<: *mlx-vlm
+  name: "mlx-vlm-development"
+  capabilities:
+    default: "cpu-mlx-vlm-development"
+    nvidia: "cuda12-mlx-vlm-development"
+    metal: "metal-mlx-vlm-development"
+    nvidia-cuda-12: "cuda12-mlx-vlm-development"
+    nvidia-cuda-13: "cuda13-mlx-vlm-development"
+    nvidia-l4t: "nvidia-l4t-mlx-vlm-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-mlx-vlm-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-mlx-vlm-development"
 - !!merge <<: *mlx-audio
-  name: "mlx-audio-development"
+  name: "metal-mlx-audio"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-audio"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-mlx-audio
+- !!merge <<: *mlx-audio
+  name: "metal-mlx-audio-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx-audio"
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-mlx-audio
+- !!merge <<: *mlx-audio
+  name: "mlx-audio-development"
+  capabilities:
+    default: "cpu-mlx-audio-development"
+    nvidia: "cuda12-mlx-audio-development"
+    metal: "metal-mlx-audio-development"
+    nvidia-cuda-12: "cuda12-mlx-audio-development"
+    nvidia-cuda-13: "cuda13-mlx-audio-development"
+    nvidia-l4t: "nvidia-l4t-mlx-audio-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-mlx-audio-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-mlx-audio-development"
 - !!merge <<: *mlx-distributed
-  name: "mlx-distributed-development"
+  name: "metal-mlx-distributed"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-distributed"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-mlx-distributed
+- !!merge <<: *mlx-distributed
+  name: "metal-mlx-distributed-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx-distributed"
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-mlx-distributed
+- !!merge <<: *mlx-distributed
+  name: "mlx-distributed-development"
+  capabilities:
+    default: "cpu-mlx-distributed-development"
+    nvidia: "cuda12-mlx-distributed-development"
+    metal: "metal-mlx-distributed-development"
+    nvidia-cuda-12: "cuda12-mlx-distributed-development"
+    nvidia-cuda-13: "cuda13-mlx-distributed-development"
+    nvidia-l4t: "nvidia-l4t-mlx-distributed-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-mlx-distributed-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-mlx-distributed-development"
 ## mlx
 - !!merge <<: *mlx
   name: "cpu-mlx"
@@ -1571,10 +1918,20 @@
   mirrors:
     - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-distributed
 - !!merge <<: *kitten-tts
-  name: "kitten-tts-development"
+  name: "cpu-kitten-tts"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-kitten-tts"
+  mirrors:
+    - localai/localai-backends:latest-kitten-tts
+- !!merge <<: *kitten-tts
+  name: "cpu-kitten-tts-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-kitten-tts"
   mirrors:
     - localai/localai-backends:master-kitten-tts
+- !!merge <<: *kitten-tts
+  name: "kitten-tts-development"
+  capabilities:
+    default: "cpu-kitten-tts-development"
+    metal: "metal-kitten-tts-development"
 - !!merge <<: *kitten-tts
   name: "metal-kitten-tts"
   uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-kitten-tts"
@@ -1586,11 +1943,23 @@
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-kitten-tts
 - !!merge <<: *local-store
-  name: "local-store-development"
+  name: "cpu-local-store"
+  alias: "local-store"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-local-store"
+  mirrors:
+    - localai/localai-backends:latest-cpu-local-store
+- !!merge <<: *local-store
+  name: "cpu-local-store-development"
   alias: "local-store"
   uri: "quay.io/go-skynet/local-ai-backends:master-cpu-local-store"
   mirrors:
     - localai/localai-backends:master-cpu-local-store
+- !!merge <<: *local-store
+  name: "local-store-development"
+  alias: "local-store"
+  capabilities:
+    default: "cpu-local-store-development"
+    metal: "metal-local-store-development"
 - !!merge <<: *local-store
   name: "metal-local-store"
   uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-local-store"
@@ -1603,7 +1972,12 @@
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-local-store
 - !!merge <<: *opus
-  name: "opus-development"
+  name: "cpu-opus"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-opus"
+  mirrors:
+    - localai/localai-backends:latest-cpu-opus
+- !!merge <<: *opus
+  name: "cpu-opus-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-cpu-opus"
   mirrors:
     - localai/localai-backends:master-cpu-opus
@@ -1618,10 +1992,20 @@
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-opus
 - !!merge <<: *silero-vad
-  name: "silero-vad-development"
+  name: "cpu-silero-vad"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-silero-vad"
+  mirrors:
+    - localai/localai-backends:latest-cpu-silero-vad
+- !!merge <<: *silero-vad
+  name: "cpu-silero-vad-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-cpu-silero-vad"
   mirrors:
     - localai/localai-backends:master-cpu-silero-vad
+- !!merge <<: *silero-vad
+  name: "silero-vad-development"
+  capabilities:
+    default: "cpu-silero-vad-development"
+    metal: "metal-silero-vad-development"
 - !!merge <<: *silero-vad
   name: "metal-silero-vad"
   uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-silero-vad"
@@ -1633,10 +2017,20 @@
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-silero-vad
 - !!merge <<: *piper
-  name: "piper-development"
+  name: "cpu-piper"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-piper"
+  mirrors:
+    - localai/localai-backends:latest-piper
+- !!merge <<: *piper
+  name: "cpu-piper-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-piper"
   mirrors:
     - localai/localai-backends:master-piper
+- !!merge <<: *piper
+  name: "piper-development"
+  capabilities:
+    default: "cpu-piper-development"
+    metal: "metal-piper-development"
 - !!merge <<: *piper
   name: "metal-piper"
   uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-piper"
@@ -2345,6 +2739,37 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-stablediffusion-ggml"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-stablediffusion-ggml
+## privacy-filter
+- !!merge <<: *privacyfilter
+  name: "cpu-privacy-filter"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-privacy-filter"
+  mirrors:
+    - localai/localai-backends:latest-cpu-privacy-filter
+- !!merge <<: *privacyfilter
+  name: "cpu-privacy-filter-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-privacy-filter"
+  mirrors:
+    - localai/localai-backends:master-cpu-privacy-filter
+- !!merge <<: *privacyfilter
+  name: "vulkan-privacy-filter"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-privacy-filter"
+  mirrors:
+    - localai/localai-backends:latest-gpu-vulkan-privacy-filter
+- !!merge <<: *privacyfilter
+  name: "vulkan-privacy-filter-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-privacy-filter"
+  mirrors:
+    - localai/localai-backends:master-gpu-vulkan-privacy-filter
+- !!merge <<: *privacyfilter
+  name: "cuda13-privacy-filter"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-privacy-filter"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-privacy-filter
+- !!merge <<: *privacyfilter
+  name: "cuda13-privacy-filter-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-privacy-filter"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-privacy-filter
 # vllm
 - !!merge <<: *vllm
   name: "vllm-development"
@@ -3279,6 +3704,121 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-qwen3-tts-cpp"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-qwen3-tts-cpp
+## omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "omnivoice-cpp-development"
+  capabilities:
+    default: "cpu-omnivoice-cpp-development"
+    nvidia: "cuda12-omnivoice-cpp-development"
+    nvidia-cuda-13: "cuda13-omnivoice-cpp-development"
+    nvidia-cuda-12: "cuda12-omnivoice-cpp-development"
+    intel: "intel-sycl-f16-omnivoice-cpp-development"
+    metal: "metal-omnivoice-cpp-development"
+    amd: "rocm-omnivoice-cpp-development"
+    vulkan: "vulkan-omnivoice-cpp-development"
+    nvidia-l4t: "nvidia-l4t-arm64-omnivoice-cpp-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-omnivoice-cpp-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-omnivoice-cpp-development"
+- !!merge <<: *omnivoicecpp
+  name: "nvidia-l4t-arm64-omnivoice-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-arm64-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "nvidia-l4t-arm64-omnivoice-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-arm64-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "cuda13-nvidia-l4t-arm64-omnivoice-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "cuda13-nvidia-l4t-arm64-omnivoice-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "cpu-omnivoice-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:latest-cpu-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "metal-omnivoice-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "metal-omnivoice-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "cpu-omnivoice-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:master-cpu-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "cuda12-omnivoice-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "rocm-omnivoice-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-rocm-hipblas-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "intel-sycl-f32-omnivoice-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-sycl-f32-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "intel-sycl-f16-omnivoice-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-sycl-f16-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "vulkan-omnivoice-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-vulkan-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "vulkan-omnivoice-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-vulkan-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "cuda12-omnivoice-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "rocm-omnivoice-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-rocm-hipblas-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "intel-sycl-f32-omnivoice-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-sycl-f32-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "intel-sycl-f16-omnivoice-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-sycl-f16-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "cuda13-omnivoice-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-omnivoice-cpp
+- !!merge <<: *omnivoicecpp
+  name: "cuda13-omnivoice-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-omnivoice-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-omnivoice-cpp
 ## vibevoice-cpp
 - !!merge <<: *vibevoicecpp
   name: "nvidia-l4t-arm64-vibevoice-cpp"
@@ -4609,24 +5149,24 @@
     - localai/localai-backends:master-cpu-trl
 - !!merge <<: *trl
   name: "cuda12-trl"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-cublas-cuda12-trl"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-trl"
   mirrors:
-    - localai/localai-backends:latest-cublas-cuda12-trl
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-trl
 - !!merge <<: *trl
   name: "cuda12-trl-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-cublas-cuda12-trl"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-trl"
   mirrors:
-    - localai/localai-backends:master-cublas-cuda12-trl
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-trl
 - !!merge <<: *trl
   name: "cuda13-trl"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-cublas-cuda13-trl"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-trl"
   mirrors:
-    - localai/localai-backends:latest-cublas-cuda13-trl
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-trl
 - !!merge <<: *trl
   name: "cuda13-trl-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-cublas-cuda13-trl"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-trl"
   mirrors:
-    - localai/localai-backends:master-cublas-cuda13-trl
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-trl
 ## llama.cpp quantization backend
 - &llama-cpp-quantization
   name: "llama-cpp-quantization"
@@ -4793,3 +5333,18 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-sherpa-onnx"
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-sherpa-onnx
+## supertonic
+- !!merge <<: *supertonic
+  name: "supertonic-development"
+  capabilities:
+    default: "cpu-supertonic-development"
+- !!merge <<: *supertonic
+  name: "cpu-supertonic"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-supertonic"
+  mirrors:
+    - localai/localai-backends:latest-cpu-supertonic
+- !!merge <<: *supertonic
+  name: "cpu-supertonic-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-supertonic"
+  mirrors:
+    - localai/localai-backends:master-cpu-supertonic

backend/python/neutts/requirements-cpu.txt

@@ -1,6 +1,7 @@
 --extra-index-url https://download.pytorch.org/whl/cpu
 accelerate
 torch==2.8.0
+torchaudio==2.8.0
 transformers==4.56.1
 librosa==0.11.0
 neucodec>=0.0.4

backend/python/neutts/requirements-cublas12.txt

@@ -3,6 +3,7 @@ neucodec>=0.0.4
 phonemizer==3.3.0
 soundfile==0.13.1
 torch==2.8.0
+torchaudio==2.8.0
 transformers==4.56.1
 resemble-perth==1.0.1
 accelerate

backend/python/transformers/backend.py

@@ -270,10 +270,17 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
 
     def TokenClassify(self, request, context):
         # Runs HuggingFace's token-classification pipeline and returns
-        # the aggregated entity spans. The pipeline gives us byte
-        # offsets via aggregation_strategy="simple" (set at load
-        # time), so the caller can slice the original text without
-        # re-tokenising on the Go side.
+        # the aggregated entity spans.
+        #
+        # OFFSET UNITS: the proto contract (TokenClassifyEntity.start/end)
+        # is UTF-8 BYTE offsets into request.text. HuggingFace's pipeline,
+        # however, reports start/end as CODEPOINT offsets into the Python
+        # str (derived from the fast tokenizer's offset_mapping). Those
+        # coincide only for ASCII; for any multi-byte character they
+        # diverge — and this entry point exists to serve the explicitly
+        # multilingual privacy-filter model, so the conversion is
+        # mandatory, not a nicety. We build one prefix table mapping each
+        # codepoint index to its byte offset and translate every span.
         if not getattr(self, "TokenClassification", False):
             context.set_code(grpc.StatusCode.FAILED_PRECONDITION)
             context.set_details("model was not loaded as Type=TokenClassification")
@@ -286,18 +293,50 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             context.set_details(f"token-classification failed: {err}")
             return backend_pb2.TokenClassifyResponse()
 
+        text = request.text
+        # byte_at[i] = byte length of text[:i]; len == len(text)+1 so an
+        # exclusive end offset that points one past the last codepoint
+        # maps to len(text.encode("utf-8")). Built in a single O(n) pass.
+        byte_at = [0] * (len(text) + 1)
+        acc = 0
+        for i, ch in enumerate(text):
+            byte_at[i] = acc
+            acc += len(ch.encode("utf-8"))
+        byte_at[len(text)] = acc
+
+        def to_byte(cp_index, default):
+            # Clamp out-of-range codepoint indices into the table rather
+            # than throwing: a span we can't place is better dropped Go-side
+            # than crashing the RPC.
+            if cp_index is None:
+                cp_index = default
+            if cp_index < 0:
+                cp_index = 0
+            elif cp_index > len(text):
+                cp_index = len(text)
+            return byte_at[cp_index]
+
         threshold = request.threshold if request.threshold > 0 else 0.0
         entities = []
         for r in results:
             score = float(r.get("score", 0.0))
             if score < threshold:
                 continue
+            cp_start = r.get("start")
+            cp_end = r.get("end")
+            start = to_byte(cp_start, 0)
+            end = to_byte(cp_end, 0)
             entities.append(backend_pb2.TokenClassifyEntity(
                 entity_group=str(r.get("entity_group") or r.get("entity") or ""),
-                start=int(r.get("start", 0)),
-                end=int(r.get("end", 0)),
+                start=start,
+                end=end,
                 score=score,
-                text=str(r.get("word", "")),
+                # Slice the original text by the (codepoint) span so the
+                # echoed text matches start..end exactly, instead of the
+                # pipeline's reconstructed "word" which can carry wordpiece
+                # artifacts. Falls back to "word" when offsets are absent.
+                text=(text[cp_start:cp_end] if cp_start is not None and cp_end is not None
+                      else str(r.get("word", ""))),
             ))
         return backend_pb2.TokenClassifyResponse(entities=entities)
 

backend/python/vllm/requirements-cublas13-after.txt

@@ -3,5 +3,5 @@
 # on a cu130 host. Pull the cu130-flavoured wheel from vLLM's per-tag index
 # instead — the cublas13 case in install.sh adds --index-strategy=unsafe-best-match
 # so uv consults this index alongside PyPI.
---extra-index-url https://wheels.vllm.ai/0.22.1/cu130
-vllm==0.22.1
+--extra-index-url https://wheels.vllm.ai/0.23.0/cu130
+vllm==0.23.0

backend/python/vllm/requirements.txt

@@ -1,4 +1,4 @@
-grpcio==1.81.0
+grpcio==1.81.1
 protobuf
 certifi
 setuptools

backend/python/whisperx/backend.py

@@ -79,6 +79,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
 
     def AudioTranscription(self, request, context):
         import whisperx
+        from whisperx.diarize import DiarizationPipeline
 
         resultSegments = []
         text = ""
@@ -106,8 +107,8 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             # Diarize if requested and HF token is available
             if request.diarize and self.hf_token:
                 if self.diarize_pipeline is None:
-                    self.diarize_pipeline = whisperx.DiarizationPipeline(
-                        use_auth_token=self.hf_token,
+                    self.diarize_pipeline = DiarizationPipeline(
+                        token=self.hf_token,
                         device=self.device,
                     )
                 diarize_segments = self.diarize_pipeline(audio)

cmd/launcher/internal/launcher.go

@@ -635,8 +635,11 @@ func (l *Launcher) showDownloadProgress(version, title string) {
 		progressBar := widget.NewProgressBar()
 		progressBar.SetValue(0)
 
-		// Status label
+		// Status label. Truncate with an ellipsis so a long "Download failed:
+		// <url>" message can't stretch the window (and progress bar) to fit the
+		// whole error on one line; the full error is shown in the dialog below.
 		statusLabel := widget.NewLabel("Preparing download...")
+		statusLabel.Truncation = fyne.TextTruncateEllipsis
 
 		// Release notes button
 		releaseNotesButton := widget.NewButton("View Release Notes", func() {

cmd/launcher/internal/systray_manager.go

@@ -454,8 +454,11 @@ func (sm *SystrayManager) showDownloadProgress(version string) {
 	progressBar := widget.NewProgressBar()
 	progressBar.SetValue(0)
 
-	// Status label
+	// Status label. Truncate with an ellipsis so a long "Download failed:
+	// <url>" message can't stretch the window (and progress bar) to fit the
+	// whole error on one line; the full error is shown in the dialog below.
 	statusLabel := widget.NewLabel("Preparing download...")
+	statusLabel.Truncation = fyne.TextTruncateEllipsis
 
 	// Release notes button
 	releaseNotesButton := widget.NewButton("View Release Notes", func() {

cmd/launcher/internal/ui.go

@@ -57,8 +57,16 @@ type LauncherUI struct {
 
 // NewLauncherUI creates a new UI instance
 func NewLauncherUI() *LauncherUI {
+	// Truncate the status text with an ellipsis. Status messages can carry a
+	// download error containing a long, unbreakable URL/path; without this the
+	// label demands the full single-line width and stretches the window (and
+	// the progress bar) arbitrarily wide. The full error is still shown in the
+	// error dialog.
+	statusLabel := widget.NewLabel("Initializing...")
+	statusLabel.Truncation = fyne.TextTruncateEllipsis
+
 	return &LauncherUI{
-		statusLabel:       widget.NewLabel("Initializing..."),
+		statusLabel:       statusLabel,
 		versionLabel:      widget.NewLabel("Version: Unknown"),
 		startStopButton:   widget.NewButton("Start LocalAI", nil),
 		webUIButton:       widget.NewButton("Open WebUI", nil),
@@ -602,8 +610,11 @@ func (ui *LauncherUI) showDownloadProgress(version, title string) {
 		progressBar := widget.NewProgressBar()
 		progressBar.SetValue(0)
 
-		// Status label
+		// Status label. Truncate with an ellipsis so a long "Download failed:
+		// <url>" message can't stretch the window (and progress bar) to fit the
+		// whole error on one line; the full error is shown in the dialog below.
 		statusLabel := widget.NewLabel("Preparing download...")
+		statusLabel.Truncation = fyne.TextTruncateEllipsis
 
 		// Release notes button
 		releaseNotesButton := widget.NewButton("View Release Notes", func() {

core/application/application.go

@@ -12,14 +12,15 @@ import (
 	"github.com/mudler/LocalAI/core/http/auth"
 	mcpTools "github.com/mudler/LocalAI/core/http/endpoints/mcp"
 	"github.com/mudler/LocalAI/core/services/agentpool"
+	"github.com/mudler/LocalAI/core/services/cloudproxy/mitm"
 	"github.com/mudler/LocalAI/core/services/facerecognition"
 	"github.com/mudler/LocalAI/core/services/galleryop"
 	"github.com/mudler/LocalAI/core/services/monitoring"
 	"github.com/mudler/LocalAI/core/services/nodes"
 	"github.com/mudler/LocalAI/core/services/routing/admission"
 	"github.com/mudler/LocalAI/core/services/routing/billing"
-	"github.com/mudler/LocalAI/core/services/cloudproxy/mitm"
 	"github.com/mudler/LocalAI/core/services/routing/pii"
+	"github.com/mudler/LocalAI/core/services/routing/piidetector"
 	"github.com/mudler/LocalAI/core/services/routing/router"
 	"github.com/mudler/LocalAI/core/services/voicerecognition"
 	"github.com/mudler/LocalAI/core/templates"
@@ -71,15 +72,15 @@ type Application struct {
 	// 1-to-1 host↔model invariant the dispatcher relies on. Read by
 	// /api/middleware/status so the admin UI can surface the cause.
 	mitmHostConflicts atomic.Pointer[map[string][]string]
-	routerDecisions    router.DecisionStore
-	routerRegistry     *router.Registry
-	admissionLimiter   *admission.Limiter
-	watchdogMutex      sync.Mutex
-	watchdogStop       chan bool
-	p2pMutex           sync.Mutex
-	p2pCtx             context.Context
-	p2pCancel          context.CancelFunc
-	agentJobMutex      sync.Mutex
+	routerDecisions   router.DecisionStore
+	routerRegistry    *router.Registry
+	admissionLimiter  *admission.Limiter
+	watchdogMutex     sync.Mutex
+	watchdogStop      chan bool
+	p2pMutex          sync.Mutex
+	p2pCtx            context.Context
+	p2pCancel         context.CancelFunc
+	agentJobMutex     sync.Mutex
 
 	// Distributed mode services (nil when not in distributed mode)
 	distributed *DistributedServices
@@ -254,6 +255,122 @@ func (a *Application) PIIEvents() pii.EventStore {
 	return a.piiEvents
 }
 
+// PIINERResolver returns the resolver the chat PII middleware uses to
+// turn a configured detector model name into a ready-to-use NERConfig:
+// a token-classifier bound over the shared model loader (lazy — the
+// model loads on first Detect) plus the detection policy read from that
+// model's own pii_detection block. Unknown names resolve to (zero,
+// false) so the middleware fails closed. Pass it via pii.WithNERResolver.
+func (a *Application) PIINERResolver() pii.NERDetectorResolver {
+	return func(modelName string) (pii.NERConfig, bool) {
+		if modelName == "" {
+			return pii.NERConfig{}, false
+		}
+		cfg, ok := a.ModelConfigLoader().GetModelConfig(modelName)
+		if !ok {
+			return pii.NERConfig{}, false
+		}
+
+		// Pattern detectors match secrets with the restricted-regex tier
+		// in-process (no backend load). Build a pattern matcher instead of the
+		// gRPC token-classifier; on a compile error fail closed with an error
+		// detector so the request is blocked, not silently unscanned.
+		if cfg.IsPatternDetector() {
+			det, err := piidetector.NewPattern(cfg, a.ApplicationConfig())
+			if err != nil {
+				det = pii.NewErrNERDetector(err.Error())
+			}
+			return pii.NERConfigFromRaw(
+				det,
+				0, // patterns are deterministic — no confidence floor
+				cfg.PIIDetectionDefaultAction(),
+				patternEntityActions(cfg),
+				pii.SourcePattern,
+			), true
+		}
+
+		det := piidetector.New(a.ModelLoader(), cfg, a.ApplicationConfig())
+		return pii.NERConfigFromRaw(
+			det,
+			cfg.PIIDetectionMinScore(),
+			cfg.PIIDetectionDefaultAction(),
+			cfg.PIIDetectionEntityActions(),
+			pii.SourceNER,
+		), true
+	}
+}
+
+// patternEntityActions merges a pattern detector's per-pattern Action overrides
+// into its entity_actions map. A pattern reports matches under its Name, so a
+// per-pattern action is just an entity_actions[Name] entry; explicit
+// entity_actions still win if both are set.
+func patternEntityActions(cfg config.ModelConfig) map[string]string {
+	out := cfg.PIIDetectionEntityActions()
+	for _, p := range cfg.PIIDetection.Patterns {
+		if p.Action == "" || p.Name == "" {
+			continue
+		}
+		if out == nil {
+			out = map[string]string{}
+		}
+		if _, exists := out[p.Name]; !exists {
+			out[p.Name] = p.Action
+		}
+	}
+	return out
+}
+
+// ResolvePIIPolicy resolves the effective request-side PII policy for a
+// consuming model, layering the instance-wide default detector
+// (PIIDefaultDetectors, set via POST /api/settings) on top of the per-model
+// config. It is the single decision point shared by the chat middleware (via
+// WithPolicyResolver) and the MITM listener so both agree.
+//
+//   - enabled: an explicit pii.enabled on the model always wins (true OR
+//     false). Otherwise PII is on when the backend defaults it on — today
+//     that means cloud-proxy models, which cross the network to a third party.
+//   - detectors: the model's own pii.detectors, or — when it lists none — the
+//     global PIIDefaultDetectors fallback. This is what makes cloud-proxy/MITM
+//     redaction work out of the box.
+//
+// appConfig is read live, so changes via the settings API take effect on the
+// next request without a restart.
+func (a *Application) ResolvePIIPolicy(cfg *config.ModelConfig) (enabled bool, detectors []string) {
+	if cfg == nil {
+		return false, nil
+	}
+	appCfg := a.ApplicationConfig()
+
+	if cfg.PII.Enabled != nil {
+		enabled = *cfg.PII.Enabled
+	} else {
+		enabled = cfg.PIIIsEnabled() // backend default (cloud-proxy)
+	}
+	if !enabled {
+		return false, nil
+	}
+
+	detectors = cfg.PIIDetectors()
+	if len(detectors) == 0 {
+		detectors = append([]string(nil), appCfg.PIIDefaultDetectors...)
+	}
+	return enabled, detectors
+}
+
+// PIIPolicyResolver adapts ResolvePIIPolicy to pii.PolicyResolver for
+// pii.WithPolicyResolver. The middleware carries the resolved model config as
+// `any` (the MODEL_CONFIG context value, a *config.ModelConfig); this asserts
+// it back and applies the instance-wide defaults.
+func (a *Application) PIIPolicyResolver() pii.PolicyResolver {
+	return func(modelCfg any) (bool, []string) {
+		cfg, ok := modelCfg.(*config.ModelConfig)
+		if !ok {
+			return false, nil
+		}
+		return a.ResolvePIIPolicy(cfg)
+	}
+}
+
 // MITMCA returns the cloudproxy MITM proxy's CA, or nil when the
 // MITM listener is disabled.
 func (a *Application) MITMCA() *mitm.CA { return a.mitmCA.Load() }

core/application/distributed.go

@@ -161,6 +161,21 @@ func initDistributed(cfg *config.ApplicationConfig, authDB *gorm.DB, configLoade
 	}
 	xlog.Info("Node registry initialized")
 
+	// Seed declarative per-model scheduling config (LOCALAI_MODEL_SCHEDULING /
+	// LOCALAI_MODEL_SCHEDULING_CONFIG). Authoritative: overwrites matching models
+	// on every boot. Runs before the reconciler starts so the first tick already
+	// sees the desired state. Models not listed are left untouched.
+	if cfg.Distributed.ModelSchedulingJSON != "" || cfg.Distributed.ModelSchedulingConfigPath != "" {
+		schedConfigs, err := nodes.ParseSchedulingSeed(cfg.Distributed.ModelSchedulingJSON, cfg.Distributed.ModelSchedulingConfigPath)
+		if err != nil {
+			return nil, fmt.Errorf("parsing declarative model scheduling config: %w", err)
+		}
+		if err := registry.SeedModelScheduling(context.Background(), schedConfigs); err != nil {
+			return nil, fmt.Errorf("seeding declarative model scheduling config: %w", err)
+		}
+		xlog.Info("Applied declarative model scheduling config", "models", len(schedConfigs))
+	}
+
 	// Collect SmartRouter option values; the router itself is created after all
 	// dependencies (including FileStager and Unloader) are ready.
 	var routerAuthToken string

core/application/mitm.go

@@ -8,6 +8,7 @@ import (
 
 	"github.com/mudler/LocalAI/core/config"
 	"github.com/mudler/LocalAI/core/services/cloudproxy/mitm"
+	"github.com/mudler/LocalAI/core/services/routing/pii"
 	"github.com/mudler/xlog"
 )
 
@@ -91,25 +92,41 @@ func startMITMLocked(app *Application, options *config.ApplicationConfig) error
 	}
 	sort.Strings(effectiveHosts)
 
-	// Per-host PII gate inherits from the owning model's pii.enabled.
-	// A non-cloud-proxy backend with no explicit pii.enabled resolves
-	// to false → host is intercepted but the regex pass is skipped
-	// (audit events still record).
-	var piiDisabled []string
+	// Per-host NER detectors come from the owning model's pii.detectors
+	// (resolved against each detector model's pii_detection policy). A
+	// host whose model has pii.enabled=false, lists no detectors, or
+	// whose detectors can't be resolved gets no entry → it is intercepted
+	// and forwarded unredacted (audit events still record traffic). An
+	// unresolvable detector is recorded as an error-detector so the
+	// request fails closed at request time rather than leaking.
+	resolver := app.PIINERResolver()
+	detectorsByHost := map[string][]pii.NERConfig{}
 	for host, modelName := range ownership.Owners {
 		cfg, exists := app.backendLoader.GetModelConfig(modelName)
 		if !exists {
 			continue
 		}
-		if !cfg.PIIIsEnabled() {
-			piiDisabled = append(piiDisabled, host)
+		// Resolve through the shared policy so cloud-proxy hosts inherit the
+		// instance-wide default detector when they name none of their own.
+		enabled, detectors := app.ResolvePIIPolicy(&cfg)
+		if !enabled || len(detectors) == 0 {
+			continue
 		}
+		cfgs := make([]pii.NERConfig, 0, len(detectors))
+		for _, name := range detectors {
+			nc, ok := resolver(name)
+			if !ok {
+				xlog.Error("mitm: detector model not resolvable; requests to host will fail closed", "host", host, "detector", name)
+				nc = pii.NERConfig{Detector: pii.NewErrNERDetector("detector model '" + name + "' not resolvable")}
+			}
+			cfgs = append(cfgs, nc)
+		}
+		detectorsByHost[host] = cfgs
 	}
 
 	handler := mitm.NewPIIHandler(mitm.PIIHandlerOptions{
-		Redactor:             app.piiRedactor,
-		EventStore:           app.piiEvents,
-		HostsWithPIIDisabled: piiDisabled,
+		EventStore:      app.piiEvents,
+		DetectorsByHost: detectorsByHost,
 	})
 
 	srv, err := mitm.NewServer(mitm.Config{
@@ -132,7 +149,7 @@ func startMITMLocked(app *Application, options *config.ApplicationConfig) error
 		"ca_dir", caDir,
 		"intercept_hosts", effectiveHosts,
 		"model_owned_hosts", len(ownership.Owners),
-		"pii_disabled_hosts", len(piiDisabled),
+		"pii_detector_hosts", len(detectorsByHost),
 	)
 	return nil
 }

core/application/pii_policy_test.go

@@ -0,0 +1,51 @@
+package application
+
+import (
+	"github.com/mudler/LocalAI/core/config"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+var _ = Describe("ResolvePIIPolicy", func() {
+	chat := config.FLAG_CHAT
+	bp := func(b bool) *bool { return &b }
+	mk := func(c *config.ApplicationConfig) *Application {
+		return &Application{applicationConfig: c}
+	}
+
+	It("lets an explicit pii.enabled=false win over the global default detector", func() {
+		app := mk(&config.ApplicationConfig{PIIDefaultDetectors: []string{"pf"}})
+		cfg := &config.ModelConfig{Backend: "cloud-proxy", KnownUsecases: &chat}
+		cfg.PII.Enabled = bp(false)
+		enabled, dets := app.ResolvePIIPolicy(cfg)
+		Expect(enabled).To(BeFalse())
+		Expect(dets).To(BeNil())
+	})
+
+	It("enables a cloud-proxy model with the global default detector (closes the no-op gap)", func() {
+		// cloud-proxy defaults PIIIsEnabled()==true but lists no detectors, so
+		// without a global default it scans with nothing.
+		app := mk(&config.ApplicationConfig{PIIDefaultDetectors: []string{"pf"}})
+		cfg := &config.ModelConfig{Backend: "cloud-proxy"}
+		enabled, dets := app.ResolvePIIPolicy(cfg)
+		Expect(enabled).To(BeTrue())
+		Expect(dets).To(Equal([]string{"pf"}))
+	})
+
+	It("leaves a non-cloud model off by default (no instance usecase default-on)", func() {
+		app := mk(&config.ApplicationConfig{PIIDefaultDetectors: []string{"pf"}})
+		cfg := &config.ModelConfig{Backend: "llama-cpp", KnownUsecases: &chat}
+		enabled, _ := app.ResolvePIIPolicy(cfg)
+		Expect(enabled).To(BeFalse())
+	})
+
+	It("prefers the model's own detectors over the global default", func() {
+		app := mk(&config.ApplicationConfig{PIIDefaultDetectors: []string{"global-pf"}})
+		cfg := &config.ModelConfig{Backend: "cloud-proxy"}
+		cfg.PII.Detectors = []string{"own-pf"}
+		enabled, dets := app.ResolvePIIPolicy(cfg)
+		Expect(enabled).To(BeTrue())
+		Expect(dets).To(Equal([]string{"own-pf"}))
+	})
+})

core/application/startup.go

@@ -53,7 +53,6 @@ func New(opts ...config.AppOption) (*Application, error) {
 	caps, err := xsysinfo.CPUCapabilities()
 	if err == nil {
 		xlog.Debug("CPU capabilities", "capabilities", caps)
-
 	}
 	gpus, err := xsysinfo.GPUs()
 	if err == nil {
@@ -68,18 +67,18 @@ func New(opts ...config.AppOption) (*Application, error) {
 		return nil, fmt.Errorf("models path cannot be empty")
 	}
 
-	err = os.MkdirAll(options.SystemState.Model.ModelsPath, 0750)
+	err = os.MkdirAll(options.SystemState.Model.ModelsPath, 0o750)
 	if err != nil {
 		return nil, fmt.Errorf("unable to create ModelPath: %q", err)
 	}
 	if options.GeneratedContentDir != "" {
-		err := os.MkdirAll(options.GeneratedContentDir, 0750)
+		err := os.MkdirAll(options.GeneratedContentDir, 0o750)
 		if err != nil {
 			return nil, fmt.Errorf("unable to create ImageDir: %q", err)
 		}
 	}
 	if options.UploadDir != "" {
-		err := os.MkdirAll(options.UploadDir, 0750)
+		err := os.MkdirAll(options.UploadDir, 0o750)
 		if err != nil {
 			return nil, fmt.Errorf("unable to create UploadDir: %q", err)
 		}
@@ -87,7 +86,7 @@ func New(opts ...config.AppOption) (*Application, error) {
 
 	// Create and migrate data directory
 	if options.DataPath != "" {
-		if err := os.MkdirAll(options.DataPath, 0750); err != nil {
+		if err := os.MkdirAll(options.DataPath, 0o750); err != nil {
 			return nil, fmt.Errorf("unable to create DataPath: %q", err)
 		}
 		// Migrate data from DynamicConfigsDir to DataPath if needed
@@ -192,44 +191,14 @@ func New(opts ...config.AppOption) (*Application, error) {
 		xlog.Info("stats: disabled by --disable-stats")
 	}
 
-	// Wire the regex PII filter. Default-on: a single-user box gets
-	// the built-in pattern set the first time it starts, with email/
-	// phone/SSN/credit-card on mask and api_key_prefix on block. If
-	// the operator wants different actions, --pii-config points at a
-	// YAML file that overrides per-id; --disable-pii turns it off
-	// entirely.
-	if !options.DisablePII {
-		patterns, err := pii.LoadConfig(options.PIIConfigPath)
-		if err != nil {
-			return nil, fmt.Errorf("pii config: %w", err)
-		}
-		application.piiRedactor = pii.NewRedactor(patterns)
-		application.piiEvents = pii.NewMemoryEventStore(0)
-		// Apply persisted per-pattern overrides — admins toggling
-		// action/disabled via the UI and clicking "Save to disk" land
-		// here on the next start. Bad ids are warned and ignored so a
-		// stale entry doesn't block startup.
-		for id, ov := range options.PIIPatternOverrides {
-			if ov.Action != nil {
-				if err := application.piiRedactor.SetAction(id, pii.Action(*ov.Action)); err != nil {
-					xlog.Warn("pii: persisted override skipped", "pattern", id, "error", err)
-					continue
-				}
-			}
-			if ov.Disabled != nil {
-				if err := application.piiRedactor.SetDisabled(id, *ov.Disabled); err != nil {
-					xlog.Warn("pii: persisted disable skipped", "pattern", id, "error", err)
-				}
-			}
-		}
-		xlog.Info("pii: filter enabled",
-			"patterns", len(patterns),
-			"config_path", options.PIIConfigPath,
-			"persisted_overrides", len(options.PIIPatternOverrides),
-		)
-	} else {
-		xlog.Info("pii: disabled by --disable-pii")
-	}
+	// Wire the PII filter subsystem. The redactor is now a stateless
+	// handle — detection is driven by per-model NER detectors
+	// (pii.detectors → the detector model's pii_detection policy), run
+	// request-side by the chat middleware and the MITM input path. The
+	// regex tier was removed; redaction is opt-in per model via
+	// PIIIsEnabled(). The event store backs the /api/pii/events audit log.
+	application.piiRedactor = &pii.Redactor{}
+	application.piiEvents = pii.NewMemoryEventStore(0)
 
 	// Wire the routing decision log. Always-on when stats are enabled —
 	// the per-router admin page reads this as the live activity feed
@@ -517,7 +486,7 @@ func startWatcher(options *config.ApplicationConfig) {
 	if _, err := os.Stat(options.DynamicConfigsDir); err != nil {
 		if os.IsNotExist(err) {
 			// We try to create the directory if it does not exist and was specified
-			if err := os.MkdirAll(options.DynamicConfigsDir, 0700); err != nil {
+			if err := os.MkdirAll(options.DynamicConfigsDir, 0o700); err != nil {
 				xlog.Error("failed creating DynamicConfigsDir", "error", err)
 			}
 		} else {
@@ -764,16 +733,6 @@ func loadRuntimeSettingsFromFile(options *config.ApplicationConfig) {
 		options.MITMListen = *settings.MITMListen
 	}
 
-	// PII pattern overrides — file is the only source; CLI flags don't
-	// reach into this map. Apply unconditionally when present; the
-	// redactor wiring below sees the result on first construction.
-	if settings.PIIPatternOverrides != nil {
-		options.PIIPatternOverrides = make(map[string]config.PIIPatternRuntimeOverride, len(*settings.PIIPatternOverrides))
-		for id, ov := range *settings.PIIPatternOverrides {
-			options.PIIPatternOverrides[id] = ov
-		}
-	}
-
 	// Backend upgrade flags
 	if settings.AutoUpgradeBackends != nil {
 		if !options.AutoUpgradeBackends {
@@ -924,7 +883,7 @@ func loadOrGenerateHMACSecret(path string) (string, error) {
 	}
 	secret := hex.EncodeToString(b)
 
-	if err := os.WriteFile(path, []byte(secret), 0600); err != nil {
+	if err := os.WriteFile(path, []byte(secret), 0o600); err != nil {
 		return "", fmt.Errorf("failed to persist HMAC secret: %w", err)
 	}
 

core/backend/depth.go

@@ -0,0 +1,66 @@
+package backend
+
+import (
+	"context"
+	"fmt"
+	"time"
+
+	"github.com/mudler/LocalAI/core/config"
+	"github.com/mudler/LocalAI/core/trace"
+	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/mudler/LocalAI/pkg/model"
+)
+
+// Depth runs depth estimation (Depth Anything 3) on the supplied image and
+// returns the full DepthResponse: per-pixel metric depth + confidence + sky,
+// camera pose (extrinsics/intrinsics), an optional 3D point cloud and any
+// requested exports (glb/colmap). The include_* flags and exports mirror the
+// DepthRequest proto so callers can ask for less work.
+func Depth(
+	ctx context.Context,
+	in *proto.DepthRequest,
+	loader *model.ModelLoader,
+	appConfig *config.ApplicationConfig,
+	modelConfig config.ModelConfig,
+) (*proto.DepthResponse, error) {
+	opts := ModelOptions(modelConfig, appConfig)
+	depthModel, err := loader.Load(opts...)
+	if err != nil {
+		recordModelLoadFailure(appConfig, modelConfig.Name, modelConfig.Backend, err, nil)
+		return nil, err
+	}
+
+	if depthModel == nil {
+		return nil, fmt.Errorf("could not load depth model")
+	}
+
+	var startTime time.Time
+	if appConfig.EnableTracing {
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
+		startTime = time.Now()
+	}
+
+	res, err := depthModel.Depth(ctx, in)
+
+	if appConfig.EnableTracing {
+		errStr := ""
+		if err != nil {
+			errStr = err.Error()
+		}
+
+		trace.RecordBackendTrace(trace.BackendTrace{
+			Timestamp: startTime,
+			Duration:  time.Since(startTime),
+			Type:      trace.BackendTraceDepth,
+			ModelName: modelConfig.Name,
+			Backend:   modelConfig.Backend,
+			Summary:   trace.TruncateString(in.GetSrc(), 200),
+			Error:     errStr,
+			Data: map[string]any{
+				"exports": in.GetExports(),
+			},
+		})
+	}
+
+	return res, err
+}

core/backend/options.go

@@ -307,11 +307,19 @@ func gRPCPredictOpts(c config.ModelConfig, modelPath string) *pb.PredictOptions
 		}
 	}
 
+	// TopK may be nil after SetDefaults for backends that don't use llama.cpp's
+	// top_k=40 default (issue #6632, e.g. mlx). proto3 int32 can't be unset, so
+	// send 0 — the value mlx actually wants (top-k disabled).
+	var topK int32
+	if c.TopK != nil {
+		topK = int32(*c.TopK)
+	}
+
 	pbOpts := &pb.PredictOptions{
 		Temperature:         float32(*c.Temperature),
 		TopP:                float32(*c.TopP),
 		NDraft:              c.NDraft,
-		TopK:                int32(*c.TopK),
+		TopK:                topK,
 		MinP:                float32(*c.MinP),
 		Tokens:              int32(*c.Maxtokens),
 		Threads:             int32(*c.Threads),
@@ -360,6 +368,25 @@ func gRPCPredictOpts(c config.ModelConfig, modelPath string) *pb.PredictOptions
 	if c.ReasoningEffort != "" {
 		metadata["reasoning_effort"] = c.ReasoningEffort
 	}
+	// Client request metadata overrides the server-derived reasoning levers and
+	// reaches every backend through these standalone string keys (Python backends
+	// read them directly). The reserved blob key is server-owned and skipped.
+	for k, v := range c.RequestMetadata {
+		if k == "chat_template_kwargs" {
+			continue
+		}
+		metadata[k] = v
+	}
+	// Build the generic chat_template_kwargs blob (model config map + coerced
+	// metadata) for llama.cpp and write it LAST so a client cannot clobber it.
+	if blob := c.ResolveChatTemplateKwargs(metadata); len(blob) > 0 {
+		b, err := json.Marshal(blob)
+		if err != nil {
+			xlog.Warn("failed to marshal chat_template_kwargs", "error", err)
+		} else {
+			metadata["chat_template_kwargs"] = string(b)
+		}
+	}
 	pbOpts.Metadata = metadata
 
 	// Logprobs and TopLogprobs are set by the caller if provided

core/backend/options_internal_test.go

@@ -161,3 +161,67 @@ var _ = Describe("grpcModelOpts NBatch", func() {
 		Expect(opts.ContextSize).To(BeEquivalentTo(4096), "n_batch must match the effective n_ctx the backend receives")
 	})
 })
+
+// Guards the generic chat_template_kwargs forwarding: the model config map plus any
+// per-request metadata overrides are merged, coerced, and serialised into the
+// backend metadata blob that llama.cpp reads. Client metadata also overrides the
+// server-derived standalone enable_thinking key (cross-backend consistency).
+var _ = Describe("gRPCPredictOpts chat_template_kwargs metadata", func() {
+	baseCfg := func() config.ModelConfig {
+		cfg := config.ModelConfig{}
+		cfg.SetDefaults()
+		return cfg
+	}
+
+	It("serialises the config map into the chat_template_kwargs blob", func() {
+		cfg := baseCfg()
+		cfg.ChatTemplateKwargs = map[string]any{"preserve_thinking": true}
+		opts := gRPCPredictOpts(cfg, "/tmp/models")
+		Expect(opts.Metadata).To(HaveKey("chat_template_kwargs"))
+		var blob map[string]any
+		Expect(json.Unmarshal([]byte(opts.Metadata["chat_template_kwargs"]), &blob)).To(Succeed())
+		Expect(blob).To(HaveKeyWithValue("preserve_thinking", true))
+	})
+
+	It("serialises reasoning_effort into the blob as a JSON string", func() {
+		cfg := baseCfg()
+		cfg.ReasoningEffort = "high"
+		opts := gRPCPredictOpts(cfg, "/tmp/models")
+		Expect(opts.Metadata).To(HaveKey("chat_template_kwargs"))
+		var blob map[string]any
+		Expect(json.Unmarshal([]byte(opts.Metadata["chat_template_kwargs"]), &blob)).To(Succeed())
+		// reasoning_effort must remain a string in the blob (jinja templates that
+		// key on the level read a string), unlike enable_thinking which is a bool.
+		Expect(blob["reasoning_effort"]).To(BeAssignableToTypeOf(""))
+		Expect(blob).To(HaveKeyWithValue("reasoning_effort", "high"))
+	})
+
+	It("lets client request metadata override the server-derived enable_thinking key", func() {
+		cfg := baseCfg()
+		disable := true
+		cfg.ReasoningConfig = reasoning.Config{DisableReasoning: &disable} // server: enable_thinking=false
+		cfg.RequestMetadata = map[string]string{"enable_thinking": "true"} // client overrides
+		opts := gRPCPredictOpts(cfg, "/tmp/models")
+		// standalone key (Python backends) reflects the client override
+		Expect(opts.Metadata).To(HaveKeyWithValue("enable_thinking", "true"))
+		// blob (llama.cpp) reflects it too, as a real bool
+		var blob map[string]any
+		Expect(json.Unmarshal([]byte(opts.Metadata["chat_template_kwargs"]), &blob)).To(Succeed())
+		Expect(blob).To(HaveKeyWithValue("enable_thinking", true))
+	})
+
+	It("does not let a client clobber the blob via a chat_template_kwargs metadata key", func() {
+		cfg := baseCfg()
+		cfg.ChatTemplateKwargs = map[string]any{"preserve_thinking": true}
+		cfg.RequestMetadata = map[string]string{"chat_template_kwargs": "{\"preserve_thinking\": false}"}
+		opts := gRPCPredictOpts(cfg, "/tmp/models")
+		var blob map[string]any
+		Expect(json.Unmarshal([]byte(opts.Metadata["chat_template_kwargs"]), &blob)).To(Succeed())
+		Expect(blob).To(HaveKeyWithValue("preserve_thinking", true))
+	})
+
+	It("omits the blob when there is nothing to forward", func() {
+		opts := gRPCPredictOpts(baseCfg(), "/tmp/models")
+		Expect(opts.Metadata).ToNot(HaveKey("chat_template_kwargs"))
+	})
+})

core/backend/token_classify.go

@@ -0,0 +1,150 @@
+package backend
+
+import (
+	"context"
+	"time"
+
+	"github.com/mudler/LocalAI/core/config"
+	"github.com/mudler/LocalAI/core/trace"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	model "github.com/mudler/LocalAI/pkg/model"
+)
+
+// TokenEntity is one detected span from a token-classification (NER)
+// model. Mirrors pb.TokenClassifyEntity but keeps the proto type out of
+// consumers. Start/End are BYTE offsets into the classified text,
+// half-open (addressing text[Start:End]) — the proto contract. Group is
+// the model's entity label (e.g. "private_person", "EMAIL").
+type TokenEntity struct {
+	Group string  `json:"group"`
+	Start int     `json:"start"`
+	End   int     `json:"end"`
+	Score float32 `json:"score"`
+	Text  string  `json:"text"`
+}
+
+// TokenClassifyOptions controls a single TokenClassify request.
+type TokenClassifyOptions struct {
+	// Threshold drops entities the backend scores below this value at
+	// the source. 0 returns everything the model emits; downstream
+	// callers (e.g. the PII redactor's MinScore) can still filter
+	// further once they know the per-request policy.
+	Threshold float32
+}
+
+// TokenClassifier runs a token-classification model over text and
+// returns the detected entity spans. Implemented by NewTokenClassifier
+// over a model-loaded backend; the PII redactor's encoder/NER tier
+// consumes this via a pii.NERDetector adapter (see
+// core/services/routing/piidetector).
+type TokenClassifier interface {
+	TokenClassify(ctx context.Context, text string) ([]TokenEntity, error)
+}
+
+// NewTokenClassifier binds (loader, modelConfig, appConfig) into a
+// TokenClassifier. The underlying backend is resolved lazily on the
+// first call, mirroring NewScorer.
+func NewTokenClassifier(loader *model.ModelLoader, modelConfig config.ModelConfig, appConfig *config.ApplicationConfig, opts TokenClassifyOptions) TokenClassifier {
+	return &modelTokenClassifier{loader: loader, modelConfig: modelConfig, appConfig: appConfig, opts: opts}
+}
+
+type modelTokenClassifier struct {
+	loader      *model.ModelLoader
+	modelConfig config.ModelConfig
+	appConfig   *config.ApplicationConfig
+	opts        TokenClassifyOptions
+}
+
+func (m *modelTokenClassifier) TokenClassify(ctx context.Context, text string) ([]TokenEntity, error) {
+	fn, err := ModelTokenClassify(text, m.opts, m.loader, m.modelConfig, m.appConfig)
+	if err != nil {
+		return nil, err
+	}
+	return fn(ctx)
+}
+
+// ModelTokenClassify loads the backend for modelConfig and returns a
+// closure that classifies `text`. Mirrors ModelScore: the closure is
+// bound to the loaded model so a caller can reuse it within a request
+// without re-resolving the backend.
+//
+// When tracing is enabled it records a BackendTraceTokenClassify row so the
+// detector's output — every entity's group, byte range, confidence and the
+// matched substring — shows in the Traces UI alongside the request it gated.
+// This is the technical view for debugging false positives (e.g. a phone
+// number scored as SSN); the persisted PIIEvent keeps only a hash.
+func ModelTokenClassify(text string, opts TokenClassifyOptions, loader *model.ModelLoader, modelConfig config.ModelConfig, appConfig *config.ApplicationConfig) (func(ctx context.Context) ([]TokenEntity, error), error) {
+	modelOpts := ModelOptions(modelConfig, appConfig)
+	inferenceModel, err := loader.Load(modelOpts...)
+	if err != nil {
+		recordModelLoadFailure(appConfig, modelConfig.Name, modelConfig.Backend, err, nil)
+		return nil, err
+	}
+	return func(ctx context.Context) ([]TokenEntity, error) {
+		var startTime time.Time
+		if appConfig.EnableTracing {
+			trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
+			startTime = time.Now()
+		}
+		resp, err := inferenceModel.TokenClassify(ctx, &pb.TokenClassifyRequest{
+			Text:      text,
+			Threshold: opts.Threshold,
+		})
+		entities := tokenClassifyResponseToEntities(resp)
+		if appConfig.EnableTracing {
+			trace.RecordBackendTrace(tokenClassifyTrace(modelConfig, text, opts.Threshold, entities, startTime, err))
+		}
+		if err != nil {
+			return nil, err
+		}
+		return entities, nil
+	}, nil
+}
+
+// tokenClassifyTrace assembles the Traces-UI row for one NER call: the input
+// preview, the threshold, and every detected entity (group, byte range,
+// confidence, matched text). Split out from the closure so the Data assembly
+// is unit-testable without a live backend.
+func tokenClassifyTrace(modelConfig config.ModelConfig, text string, threshold float32, entities []TokenEntity, start time.Time, callErr error) trace.BackendTrace {
+	errStr := ""
+	if callErr != nil {
+		errStr = callErr.Error()
+	}
+	return trace.BackendTrace{
+		Timestamp: start,
+		Duration:  time.Since(start),
+		Type:      trace.BackendTraceTokenClassify,
+		ModelName: modelConfig.Name,
+		Backend:   modelConfig.Backend,
+		Summary:   trace.TruncateString(text, 200),
+		Error:     errStr,
+		Data: map[string]any{
+			"input_chars": len(text),
+			"threshold":   threshold,
+			"entities":    entities,
+		},
+	}
+}
+
+// tokenClassifyResponseToEntities converts the wire-format response into
+// the value type consumed by callers. Extracted so the conversion can be
+// unit-tested without a real backend (see token_classify_test.go).
+func tokenClassifyResponseToEntities(resp *pb.TokenClassifyResponse) []TokenEntity {
+	if resp == nil {
+		return nil
+	}
+	out := make([]TokenEntity, 0, len(resp.Entities))
+	for _, e := range resp.Entities {
+		if e == nil {
+			continue
+		}
+		out = append(out, TokenEntity{
+			Group: e.EntityGroup,
+			Start: int(e.Start),
+			End:   int(e.End),
+			Score: e.Score,
+			Text:  e.Text,
+		})
+	}
+	return out
+}

core/backend/token_classify_test.go

@@ -0,0 +1,61 @@
+package backend
+
+import (
+	"errors"
+	"time"
+
+	"github.com/mudler/LocalAI/core/config"
+	"github.com/mudler/LocalAI/core/trace"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+var _ = Describe("tokenClassifyResponseToEntities", func() {
+	It("returns nil for a nil response", func() {
+		Expect(tokenClassifyResponseToEntities(nil)).To(BeNil())
+	})
+
+	It("maps proto entities to TokenEntity, skipping nil rows", func() {
+		resp := &pb.TokenClassifyResponse{
+			Entities: []*pb.TokenClassifyEntity{
+				{EntityGroup: "private_person", Start: 3, End: 8, Score: 0.97, Text: "Alice"},
+				nil,
+				{EntityGroup: "EMAIL", Start: 20, End: 40, Score: 0.5, Text: "a@b.com"},
+			},
+		}
+		Expect(tokenClassifyResponseToEntities(resp)).To(Equal([]TokenEntity{
+			{Group: "private_person", Start: 3, End: 8, Score: 0.97, Text: "Alice"},
+			{Group: "EMAIL", Start: 20, End: 40, Score: 0.5, Text: "a@b.com"},
+		}))
+	})
+
+	It("returns an empty (non-nil) slice for a response with no entities", func() {
+		out := tokenClassifyResponseToEntities(&pb.TokenClassifyResponse{})
+		Expect(out).NotTo(BeNil())
+		Expect(out).To(BeEmpty())
+	})
+})
+
+var _ = Describe("tokenClassifyTrace", func() {
+	cfg := config.ModelConfig{Name: "privacy-filter", Backend: "privacy-filter"}
+	ents := []TokenEntity{{Group: "SSN", Start: 5, End: 16, Score: 0.62, Text: "123-45-6789"}}
+
+	It("captures model, input preview, threshold and per-entity detail", func() {
+		tr := tokenClassifyTrace(cfg, "ssn is 123-45-6789", 0.5, ents, time.Now(), nil)
+		Expect(tr.Type).To(Equal(trace.BackendTraceTokenClassify))
+		Expect(tr.ModelName).To(Equal("privacy-filter"))
+		Expect(tr.Backend).To(Equal("privacy-filter"))
+		Expect(tr.Summary).To(ContainSubstring("ssn is"))
+		Expect(tr.Error).To(BeEmpty())
+		Expect(tr.Data["input_chars"]).To(Equal(len("ssn is 123-45-6789")))
+		Expect(tr.Data["threshold"]).To(BeEquivalentTo(float32(0.5)))
+		Expect(tr.Data["entities"]).To(Equal(ents))
+	})
+
+	It("records the backend error string when the call failed", func() {
+		tr := tokenClassifyTrace(cfg, "x", 0, nil, time.Now(), errors.New("boom"))
+		Expect(tr.Error).To(Equal("boom"))
+	})
+})

core/cli/run.go

@@ -172,6 +172,8 @@ type RunCMD struct {
 	NatsTLSCert               string `env:"LOCALAI_NATS_TLS_CERT" type:"existingfile" help:"Client certificate for NATS mTLS" group:"distributed"`
 	NatsTLSKey                string `env:"LOCALAI_NATS_TLS_KEY" type:"existingfile" help:"Client private key for NATS mTLS" group:"distributed"`
 	ExposeNodeHeader          bool   `env:"LOCALAI_EXPOSE_NODE_HEADER" default:"false" help:"Set the X-LocalAI-Node response header on inference responses (OpenAI chat/completions/embeddings, Anthropic /v1/messages, Ollama /api/chat,/api/generate,/api/embed) with the ID of the worker that served the request. Disabled by default: the node ID reveals internal topology and should not be exposed on a public endpoint. Best-effort: under heavy concurrency the header may reflect a recent routing decision rather than this exact request's." group:"distributed"`
+	ModelScheduling           string `env:"LOCALAI_MODEL_SCHEDULING" help:"Declarative per-model scheduling config applied at startup (inline JSON list of {model_name,node_selector,min_replicas,max_replicas,replicas:\"all\"}). Authoritative: overwrites matching models on every boot. Distributed mode only." group:"distributed"`
+	ModelSchedulingConfig     string `env:"LOCALAI_MODEL_SCHEDULING_CONFIG" help:"Path to a YAML file with the same per-model scheduling list as LOCALAI_MODEL_SCHEDULING. Distributed mode only." group:"distributed"`
 
 	Version bool
 
@@ -347,6 +349,15 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
 	if r.ExposeNodeHeader {
 		opts = append(opts, config.WithExposeNodeHeader(true))
 	}
+	if r.ModelScheduling != "" {
+		opts = append(opts, config.WithModelSchedulingJSON(r.ModelScheduling))
+	}
+	if r.ModelSchedulingConfig != "" {
+		opts = append(opts, config.WithModelSchedulingConfigPath(r.ModelSchedulingConfig))
+	}
+	if !r.Distributed && (r.ModelScheduling != "" || r.ModelSchedulingConfig != "") {
+		xlog.Warn("LOCALAI_MODEL_SCHEDULING / LOCALAI_MODEL_SCHEDULING_CONFIG is set but distributed mode is disabled (LOCALAI_DISTRIBUTED=false) - ignoring")
+	}
 
 	if r.DisableMetricsEndpoint {
 		opts = append(opts, config.DisableMetricsEndpoint)