avoid pinning version for cuda12

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

.github/workflows/backend.yml

@@ -52,6 +52,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2204'
+          - build-type: 'l4t'
+            cuda-major-version: "12"
+            cuda-minor-version: "0"
+            platforms: 'linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-nvidia-l4t-ace-step'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+            skip-drivers: 'true'
+            backend: "ace-step"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2204'
           - build-type: ''
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -104,6 +117,58 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
+          - build-type: ''
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-cpu-ace-step'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'true'
+            backend: "ace-step"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
+          - build-type: ''
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-cpu-mlx'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'true'
+            backend: "mlx"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
+          - build-type: ''
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-cpu-mlx-vlm'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'true'
+            backend: "mlx-vlm"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
+          - build-type: ''
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-cpu-mlx-audio'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'true'
+            backend: "mlx-audio"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           # CUDA 12 builds
           - build-type: 'cublas'
             cuda-major-version: "12"
@@ -248,6 +313,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             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-ace-step'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "ace-step"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "8"
@@ -300,6 +378,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             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-outetts'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "outetts"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "8"
@@ -326,6 +417,45 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             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-mlx'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "mlx"
+            dockerfile: "./backend/Dockerfile.python"
+            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-mlx-vlm'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "mlx-vlm"
+            dockerfile: "./backend/Dockerfile.python"
+            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-mlx-audio'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "mlx-audio"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "8"
@@ -509,6 +639,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             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-ace-step'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "ace-step"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'l4t'
             cuda-major-version: "13"
             cuda-minor-version: "0"
@@ -574,6 +717,45 @@ jobs:
             backend: "diffusers"
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
+          - build-type: 'l4t'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-nvidia-l4t-cuda-13-arm64-mlx'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            ubuntu-version: '2404'
+            backend: "mlx"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+          - build-type: 'l4t'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-nvidia-l4t-cuda-13-arm64-mlx-vlm'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            ubuntu-version: '2404'
+            backend: "mlx-vlm"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+          - build-type: 'l4t'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-nvidia-l4t-cuda-13-arm64-mlx-audio'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            ubuntu-version: '2404'
+            backend: "mlx-audio"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
           - build-type: 'cublas'
             cuda-major-version: "13"
             cuda-minor-version: "0"
@@ -639,6 +821,45 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             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-mlx'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "mlx"
+            dockerfile: "./backend/Dockerfile.python"
+            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-mlx-vlm'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "mlx-vlm"
+            dockerfile: "./backend/Dockerfile.python"
+            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-mlx-audio'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "mlx-audio"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "13"
             cuda-minor-version: "0"
@@ -783,6 +1004,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
+          - build-type: 'hipblas'
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-rocm-hipblas-ace-step'
+            runs-on: 'arc-runner-set'
+            base-image: "rocm/dev-ubuntu-24.04:6.4.4"
+            skip-drivers: 'false'
+            backend: "ace-step"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           # ROCm additional backends
           - build-type: 'hipblas'
             cuda-major-version: ""
@@ -980,6 +1214,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
+          - build-type: 'intel'
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-intel-ace-step'
+            runs-on: 'ubuntu-latest'
+            base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+            skip-drivers: 'false'
+            backend: "ace-step"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'l4t'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -1045,6 +1292,45 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2204'
+          - build-type: 'l4t'
+            cuda-major-version: "12"
+            cuda-minor-version: "0"
+            platforms: 'linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-nvidia-l4t-mlx'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+            skip-drivers: 'true'
+            backend: "mlx"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2204'
+          - build-type: 'l4t'
+            cuda-major-version: "12"
+            cuda-minor-version: "0"
+            platforms: 'linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-nvidia-l4t-mlx-vlm'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+            skip-drivers: 'true'
+            backend: "mlx-vlm"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2204'
+          - build-type: 'l4t'
+            cuda-major-version: "12"
+            cuda-minor-version: "0"
+            platforms: 'linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-nvidia-l4t-mlx-audio'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+            skip-drivers: 'true'
+            backend: "mlx-audio"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2204'
           # SYCL additional backends
           - build-type: 'intel'
             cuda-major-version: ""
@@ -1562,6 +1848,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
+          - build-type: ''
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-cpu-outetts'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'true'
+            backend: "outetts"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
   backend-jobs-darwin:
     uses: ./.github/workflows/backend_build_darwin.yml
     strategy:
@@ -1570,6 +1869,9 @@ jobs:
           - backend: "diffusers"
             tag-suffix: "-metal-darwin-arm64-diffusers"
             build-type: "mps"
+          - backend: "ace-step"
+            tag-suffix: "-metal-darwin-arm64-ace-step"
+            build-type: "mps"
           - backend: "mlx"
             tag-suffix: "-metal-darwin-arm64-mlx"
             build-type: "mps"
@@ -1590,6 +1892,64 @@ jobs:
             tag-suffix: "-metal-darwin-arm64-whisper"
             build-type: "metal"
             lang: "go"
+          - backend: "vibevoice"
+            tag-suffix: "-metal-darwin-arm64-vibevoice"
+            build-type: "mps"
+          - backend: "qwen-asr"
+            tag-suffix: "-metal-darwin-arm64-qwen-asr"
+            build-type: "mps"
+          - backend: "qwen-tts"
+            tag-suffix: "-metal-darwin-arm64-qwen-tts"
+            build-type: "mps"
+          - backend: "voxcpm"
+            tag-suffix: "-metal-darwin-arm64-voxcpm"
+            build-type: "mps"
+          - backend: "pocket-tts"
+            tag-suffix: "-metal-darwin-arm64-pocket-tts"
+            build-type: "mps"
+          - backend: "moonshine"
+            tag-suffix: "-metal-darwin-arm64-moonshine"
+            build-type: "mps"
+          - backend: "whisperx"
+            tag-suffix: "-metal-darwin-arm64-whisperx"
+            build-type: "mps"
+          - backend: "rerankers"
+            tag-suffix: "-metal-darwin-arm64-rerankers"
+            build-type: "mps"
+          - backend: "transformers"
+            tag-suffix: "-metal-darwin-arm64-transformers"
+            build-type: "mps"
+          - backend: "kokoro"
+            tag-suffix: "-metal-darwin-arm64-kokoro"
+            build-type: "mps"
+          - backend: "faster-whisper"
+            tag-suffix: "-metal-darwin-arm64-faster-whisper"
+            build-type: "mps"
+          - backend: "coqui"
+            tag-suffix: "-metal-darwin-arm64-coqui"
+            build-type: "mps"
+          - backend: "rfdetr"
+            tag-suffix: "-metal-darwin-arm64-rfdetr"
+            build-type: "mps"
+          - backend: "kitten-tts"
+            tag-suffix: "-metal-darwin-arm64-kitten-tts"
+            build-type: "mps"
+          - backend: "piper"
+            tag-suffix: "-metal-darwin-arm64-piper"
+            build-type: "metal"
+            lang: "go"
+          - backend: "silero-vad"
+            tag-suffix: "-metal-darwin-arm64-silero-vad"
+            build-type: "metal"
+            lang: "go"
+          - backend: "local-store"
+            tag-suffix: "-metal-darwin-arm64-local-store"
+            build-type: "metal"
+            lang: "go"
+          - backend: "huggingface"
+            tag-suffix: "-metal-darwin-arm64-huggingface"
+            build-type: "metal"
+            lang: "go"
     with:
       backend: ${{ matrix.backend }}
       build-type: ${{ matrix.build-type }}

.github/workflows/deploy-explorer.yaml

@@ -33,7 +33,7 @@ jobs:
         run: |
           CGO_ENABLED=0 make build
       - name: rm
-        uses: appleboy/ssh-action@v1.2.4
+        uses: appleboy/ssh-action@v1.2.5
         with:
             host: ${{ secrets.EXPLORER_SSH_HOST }}
             username: ${{ secrets.EXPLORER_SSH_USERNAME }}
@@ -53,7 +53,7 @@ jobs:
             rm: true
             target: ./local-ai
       - name: restarting
-        uses: appleboy/ssh-action@v1.2.4
+        uses: appleboy/ssh-action@v1.2.5
         with:
             host: ${{ secrets.EXPLORER_SSH_HOST }}
             username: ${{ secrets.EXPLORER_SSH_USERNAME }}

Makefile

@@ -1,5 +1,5 @@
 # Disable parallel execution for backend builds
-.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr 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/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/qwen-asr backends/voxcpm backends/whisperx
+.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr 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/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/qwen-asr backends/voxcpm backends/whisperx backends/ace-step
 
 GOCMD=go
 GOTEST=$(GOCMD) test
@@ -308,6 +308,7 @@ protogen-go-clean:
 
 prepare-test-extra: protogen-python
 	$(MAKE) -C backend/python/transformers
+	$(MAKE) -C backend/python/outetts
 	$(MAKE) -C backend/python/diffusers
 	$(MAKE) -C backend/python/chatterbox
 	$(MAKE) -C backend/python/vllm
@@ -319,9 +320,11 @@ prepare-test-extra: protogen-python
 	$(MAKE) -C backend/python/qwen-asr
 	$(MAKE) -C backend/python/voxcpm
 	$(MAKE) -C backend/python/whisperx
+	$(MAKE) -C backend/python/ace-step
 
 test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/transformers test
+	$(MAKE) -C backend/python/outetts test
 	$(MAKE) -C backend/python/diffusers test
 	$(MAKE) -C backend/python/chatterbox test
 	$(MAKE) -C backend/python/vllm test
@@ -333,6 +336,7 @@ test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/qwen-asr test
 	$(MAKE) -C backend/python/voxcpm test
 	$(MAKE) -C backend/python/whisperx test
+	$(MAKE) -C backend/python/ace-step test
 
 DOCKER_IMAGE?=local-ai
 DOCKER_AIO_IMAGE?=local-ai-aio
@@ -451,6 +455,7 @@ BACKEND_WHISPER = whisper|golang|.|false|true
 # Python backends with root context
 BACKEND_RERANKERS = rerankers|python|.|false|true
 BACKEND_TRANSFORMERS = transformers|python|.|false|true
+BACKEND_OUTETTS = outetts|python|.|false|true
 BACKEND_FASTER_WHISPER = faster-whisper|python|.|false|true
 BACKEND_COQUI = coqui|python|.|false|true
 BACKEND_RFDETR = rfdetr|python|.|false|true
@@ -468,6 +473,7 @@ BACKEND_QWEN_TTS = qwen-tts|python|.|false|true
 BACKEND_QWEN_ASR = qwen-asr|python|.|false|true
 BACKEND_VOXCPM = voxcpm|python|.|false|true
 BACKEND_WHISPERX = whisperx|python|.|false|true
+BACKEND_ACE_STEP = ace-step|python|.|false|true
 
 # Helper function to build docker image for a backend
 # Usage: $(call docker-build-backend,BACKEND_NAME,DOCKERFILE_TYPE,BUILD_CONTEXT,PROGRESS_FLAG,NEEDS_BACKEND_ARG)
@@ -499,6 +505,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_STABLEDIFFUSION_GGML)))
 $(eval $(call generate-docker-build-target,$(BACKEND_WHISPER)))
 $(eval $(call generate-docker-build-target,$(BACKEND_RERANKERS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_TRANSFORMERS)))
+$(eval $(call generate-docker-build-target,$(BACKEND_OUTETTS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_FASTER_WHISPER)))
 $(eval $(call generate-docker-build-target,$(BACKEND_COQUI)))
 $(eval $(call generate-docker-build-target,$(BACKEND_RFDETR)))
@@ -516,12 +523,13 @@ $(eval $(call generate-docker-build-target,$(BACKEND_QWEN_TTS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_QWEN_ASR)))
 $(eval $(call generate-docker-build-target,$(BACKEND_VOXCPM)))
 $(eval $(call generate-docker-build-target,$(BACKEND_WHISPERX)))
+$(eval $(call generate-docker-build-target,$(BACKEND_ACE_STEP)))
 
 # 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-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-qwen-asr docker-build-voxcpm docker-build-whisperx
+docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-qwen-asr docker-build-voxcpm docker-build-whisperx docker-build-ace-step
 
 ########################################################
 ### Mock Backend for E2E Tests

README.md

@@ -203,7 +203,8 @@ local-ai run oci://localai/phi-2:latest
 For more information, see [💻 Getting started](https://localai.io/basics/getting_started/index.html), if you are interested in our roadmap items and future enhancements, you can see the [Issues labeled as Roadmap here](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap)
 
 ## 📰 Latest project news
-
+- February 2026: [Realtime API for audio-to-audio with tool calling](https://github.com/mudler/LocalAI/pull/6245), [ACE-Step 1.5 support](https://github.com/mudler/LocalAI/pull/8396)
+- January 2026: **LocalAI 3.10.0** - Major release with Anthropic API support, Open Responses API for stateful agents, video & image generation suite (LTX-2), unified GPU backends, tool streaming & XML parsing, system-aware backend gallery, crash fixes for AVX-only CPUs and AMD VRAM reporting, request tracing, and new backends: **Moonshine** (ultra-fast transcription), **Pocket-TTS** (lightweight TTS). Vulkan arm64 builds now available. [Release notes](https://github.com/mudler/LocalAI/releases/tag/v3.10.0).
 - December 2025: [Dynamic Memory Resource reclaimer](https://github.com/mudler/LocalAI/pull/7583), [Automatic fitting of models to multiple GPUS(llama.cpp)](https://github.com/mudler/LocalAI/pull/7584), [Added Vibevoice backend](https://github.com/mudler/LocalAI/pull/7494)
 - November 2025: Major improvements to the UX. Among these: [Import models via URL](https://github.com/mudler/LocalAI/pull/7245) and [Multiple chats and history](https://github.com/mudler/LocalAI/pull/7325)
 - October 2025: 🔌 [Model Context Protocol (MCP)](https://localai.io/docs/features/mcp/) support added for agentic capabilities with external tools
@@ -269,6 +270,7 @@ LocalAI supports a comprehensive range of AI backends with multiple acceleration
 |---------|-------------|---------------------|
 | **whisper.cpp** | OpenAI Whisper in C/C++ | CUDA 12/13, ROCm, Intel SYCL, Vulkan, CPU |
 | **faster-whisper** | Fast Whisper with CTranslate2 | CUDA 12/13, ROCm, Intel, CPU |
+| **moonshine** | Ultra-fast transcription engine for low-end devices | CUDA 12/13, Metal, CPU |
 | **coqui** | Advanced TTS with 1100+ languages | CUDA 12/13, ROCm, Intel, CPU |
 | **kokoro** | Lightweight TTS model | CUDA 12/13, ROCm, Intel, CPU |
 | **chatterbox** | Production-grade TTS | CUDA 12/13, CPU |
@@ -279,6 +281,7 @@ LocalAI supports a comprehensive range of AI backends with multiple acceleration
 | **vibevoice** | Real-time TTS with voice cloning | CUDA 12/13, ROCm, Intel, CPU |
 | **pocket-tts** | Lightweight CPU-based TTS | CUDA 12/13, ROCm, Intel, CPU |
 | **qwen-tts** | High-quality TTS with custom voice, voice design, and voice cloning | CUDA 12/13, ROCm, Intel, CPU |
+| **ace-step** | Music generation from text descriptions, lyrics, or audio samples | CUDA 12/13, ROCm, Intel, Metal, CPU |
 
 ### Image & Video Generation
 | Backend | Description | Acceleration Support |
@@ -300,11 +303,11 @@ LocalAI supports a comprehensive range of AI backends with multiple acceleration
 |-------------------|-------------------|------------------|
 | **NVIDIA CUDA 12** | All CUDA-compatible backends | Nvidia hardware |
 | **NVIDIA CUDA 13** | All CUDA-compatible backends | Nvidia hardware |
-| **AMD ROCm** | llama.cpp, whisper, vllm, transformers, diffusers, rerankers, coqui, kokoro, neutts, vibevoice, pocket-tts, qwen-tts | AMD Graphics |
-| **Intel oneAPI** | llama.cpp, whisper, stablediffusion, vllm, transformers, diffusers, rfdetr, rerankers, coqui, kokoro, vibevoice, pocket-tts, qwen-tts | Intel Arc, Intel iGPUs |
-| **Apple Metal** | llama.cpp, whisper, diffusers, MLX, MLX-VLM | Apple M1/M2/M3+ |
+| **AMD ROCm** | llama.cpp, whisper, vllm, transformers, diffusers, rerankers, coqui, kokoro, neutts, vibevoice, pocket-tts, qwen-tts, ace-step | AMD Graphics |
+| **Intel oneAPI** | llama.cpp, whisper, stablediffusion, vllm, transformers, diffusers, rfdetr, rerankers, coqui, kokoro, vibevoice, pocket-tts, qwen-tts, ace-step | Intel Arc, Intel iGPUs |
+| **Apple Metal** | llama.cpp, whisper, diffusers, MLX, MLX-VLM, moonshine, ace-step | Apple M1/M2/M3+ |
 | **Vulkan** | llama.cpp, whisper, stablediffusion | Cross-platform GPUs |
-| **NVIDIA Jetson (CUDA 12)** | llama.cpp, whisper, stablediffusion, diffusers, rfdetr | ARM64 embedded AI (AGX Orin, etc.) |
+| **NVIDIA Jetson (CUDA 12)** | llama.cpp, whisper, stablediffusion, diffusers, rfdetr, ace-step | ARM64 embedded AI (AGX Orin, etc.) |
 | **NVIDIA Jetson (CUDA 13)** | llama.cpp, whisper, stablediffusion, diffusers, rfdetr | ARM64 embedded AI (DGX Spark) |
 | **CPU Optimized** | All backends | AVX/AVX2/AVX512, quantization support |
 

backend/backend.proto

@@ -365,6 +365,14 @@ message SoundGenerationRequest {
   optional bool sample = 6;
   optional string src = 7;
   optional int32 src_divisor = 8;
+  optional bool think = 9;
+  optional string caption = 10;
+  optional string lyrics = 11;
+  optional int32 bpm = 12;
+  optional string keyscale = 13;
+  optional string language = 14;
+  optional string timesignature = 15;
+  optional bool instrumental = 17;
 }
 
 message TokenizationResponse {

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=2634ed207a17db1a54bd8df0555bd8499a6ab691
+LLAMA_VERSION?=b536eb023368701fe3564210440e2df6151c3e65
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

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?=aa1bc0d1a6dfd70dbb9f60c11df12441e03a9075
+WHISPER_CPP_VERSION?=941bdabbe4561bc6de68981aea01bc5ab05781c5
 SO_TARGET?=libgowhisper.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

backend/index.yaml

@@ -105,6 +105,7 @@
     intel: "intel-rfdetr"
     #amd: "rocm-rfdetr"
     nvidia-l4t: "nvidia-l4t-arm64-rfdetr"
+    metal: "metal-rfdetr"
     default: "cpu-rfdetr"
     nvidia-cuda-13: "cuda13-rfdetr"
     nvidia-cuda-12: "cuda12-rfdetr"
@@ -182,6 +183,15 @@
     - text-to-text
     - LLM
     - MLX
+  capabilities:
+    default: "cpu-mlx"
+    nvidia: "cuda12-mlx"
+    metal: "metal-mlx"
+    nvidia-cuda-12: "cuda12-mlx"
+    nvidia-cuda-13: "cuda13-mlx"
+    nvidia-l4t: "nvidia-l4t-mlx"
+    nvidia-l4t-cuda-12: "nvidia-l4t-mlx"
+    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"
@@ -199,6 +209,15 @@
     - vision-language
     - LLM
     - MLX
+  capabilities:
+    default: "cpu-mlx-vlm"
+    nvidia: "cuda12-mlx-vlm"
+    metal: "metal-mlx-vlm"
+    nvidia-cuda-12: "cuda12-mlx-vlm"
+    nvidia-cuda-13: "cuda13-mlx-vlm"
+    nvidia-l4t: "nvidia-l4t-mlx-vlm"
+    nvidia-l4t-cuda-12: "nvidia-l4t-mlx-vlm"
+    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"
@@ -216,6 +235,15 @@
     - text-to-audio
     - LLM
     - MLX
+  capabilities:
+    default: "cpu-mlx-audio"
+    nvidia: "cuda12-mlx-audio"
+    metal: "metal-mlx-audio"
+    nvidia-cuda-12: "cuda12-mlx-audio"
+    nvidia-cuda-13: "cuda13-mlx-audio"
+    nvidia-l4t: "nvidia-l4t-mlx-audio"
+    nvidia-l4t-cuda-12: "nvidia-l4t-mlx-audio"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-mlx-audio"
 - &rerankers
   name: "rerankers"
   alias: "rerankers"
@@ -223,6 +251,7 @@
     nvidia: "cuda12-rerankers"
     intel: "intel-rerankers"
     amd: "rocm-rerankers"
+    metal: "metal-rerankers"
 - &transformers
   name: "transformers"
   icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4
@@ -240,6 +269,7 @@
     nvidia: "cuda12-transformers"
     intel: "intel-transformers"
     amd: "rocm-transformers"
+    metal: "metal-transformers"
     nvidia-cuda-13: "cuda13-transformers"
     nvidia-cuda-12: "cuda12-transformers"
 - &diffusers
@@ -266,6 +296,38 @@
     nvidia-cuda-12: "cuda12-diffusers"
     nvidia-l4t-cuda-12: "nvidia-l4t-arm64-diffusers"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-diffusers"
+- &ace-step
+  name: "ace-step"
+  description: |
+    ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio).
+  urls:
+    - https://github.com/ace-step/ACE-Step-1.5
+  tags:
+    - music-generation
+    - sound-generation
+  alias: "ace-step"
+  capabilities:
+    nvidia: "cuda12-ace-step"
+    intel: "intel-ace-step"
+    amd: "rocm-ace-step"
+    nvidia-l4t: "nvidia-l4t-ace-step"
+    metal: "metal-ace-step"
+    default: "cpu-ace-step"
+    nvidia-cuda-13: "cuda13-ace-step"
+    nvidia-cuda-12: "cuda12-ace-step"
+    nvidia-l4t-cuda-12: "nvidia-l4t-ace-step"
+- !!merge <<: *ace-step
+  name: "ace-step-development"
+  capabilities:
+    nvidia: "cuda12-ace-step-development"
+    intel: "intel-ace-step-development"
+    amd: "rocm-ace-step-development"
+    nvidia-l4t: "nvidia-l4t-ace-step-development"
+    metal: "metal-ace-step-development"
+    default: "cpu-ace-step-development"
+    nvidia-cuda-13: "cuda13-ace-step-development"
+    nvidia-cuda-12: "cuda12-ace-step-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-ace-step-development"
 - &faster-whisper
   icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4
   description: |
@@ -282,6 +344,7 @@
     nvidia: "cuda12-faster-whisper"
     intel: "intel-faster-whisper"
     amd: "rocm-faster-whisper"
+    metal: "metal-faster-whisper"
     nvidia-cuda-13: "cuda13-faster-whisper"
     nvidia-cuda-12: "cuda12-faster-whisper"
 - &moonshine
@@ -299,6 +362,7 @@
   alias: "moonshine"
   capabilities:
     nvidia: "cuda12-moonshine"
+    metal: "metal-moonshine"
     default: "cpu-moonshine"
     nvidia-cuda-13: "cuda13-moonshine"
     nvidia-cuda-12: "cuda12-moonshine"
@@ -318,6 +382,7 @@
   capabilities:
     nvidia: "cuda12-whisperx"
     amd: "rocm-whisperx"
+    metal: "metal-whisperx"
     default: "cpu-whisperx"
     nvidia-cuda-13: "cuda13-whisperx"
     nvidia-cuda-12: "cuda12-whisperx"
@@ -340,6 +405,7 @@
     intel: "intel-kokoro"
     amd: "rocm-kokoro"
     nvidia-l4t: "nvidia-l4t-kokoro"
+    metal: "metal-kokoro"
     nvidia-cuda-13: "cuda13-kokoro"
     nvidia-cuda-12: "cuda12-kokoro"
     nvidia-l4t-cuda-12: "nvidia-l4t-arm64-kokoro"
@@ -364,9 +430,25 @@
     nvidia: "cuda12-coqui"
     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
+  urls:
+    - https://github.com/OuteAI/outetts
+  description: |
+    OuteTTS is an open-weight text-to-speech model from OuteAI (OuteAI/OuteTTS-0.3-1B).
+    Supports custom speaker voices via audio path or default speakers.
+  tags:
+    - text-to-speech
+    - TTS
+  license: apache-2.0
+  name: "outetts"
+  alias: "outetts"
+  capabilities:
+    default: "cpu-outetts"
+    nvidia-cuda-12: "cuda12-outetts"
 - &chatterbox
   urls:
     - https://github.com/resemble-ai/chatterbox
@@ -405,6 +487,7 @@
     intel: "intel-vibevoice"
     amd: "rocm-vibevoice"
     nvidia-l4t: "nvidia-l4t-vibevoice"
+    metal: "metal-vibevoice"
     default: "cpu-vibevoice"
     nvidia-cuda-13: "cuda13-vibevoice"
     nvidia-cuda-12: "cuda12-vibevoice"
@@ -427,6 +510,7 @@
     intel: "intel-qwen-tts"
     amd: "rocm-qwen-tts"
     nvidia-l4t: "nvidia-l4t-qwen-tts"
+    metal: "metal-qwen-tts"
     default: "cpu-qwen-tts"
     nvidia-cuda-13: "cuda13-qwen-tts"
     nvidia-cuda-12: "cuda12-qwen-tts"
@@ -449,6 +533,7 @@
     intel: "intel-qwen-asr"
     amd: "rocm-qwen-asr"
     nvidia-l4t: "nvidia-l4t-qwen-asr"
+    metal: "metal-qwen-asr"
     default: "cpu-qwen-asr"
     nvidia-cuda-13: "cuda13-qwen-asr"
     nvidia-cuda-12: "cuda12-qwen-asr"
@@ -470,6 +555,7 @@
     nvidia: "cuda12-voxcpm"
     intel: "intel-voxcpm"
     amd: "rocm-voxcpm"
+    metal: "metal-voxcpm"
     default: "cpu-voxcpm"
     nvidia-cuda-13: "cuda13-voxcpm"
     nvidia-cuda-12: "cuda12-voxcpm"
@@ -490,6 +576,7 @@
     intel: "intel-pocket-tts"
     amd: "rocm-pocket-tts"
     nvidia-l4t: "nvidia-l4t-pocket-tts"
+    metal: "metal-pocket-tts"
     default: "cpu-pocket-tts"
     nvidia-cuda-13: "cuda13-pocket-tts"
     nvidia-cuda-12: "cuda12-pocket-tts"
@@ -650,31 +737,234 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx-audio"
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-mlx-audio
+## mlx
+- !!merge <<: *mlx
+  name: "cpu-mlx"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-mlx"
+  mirrors:
+    - localai/localai-backends:latest-cpu-mlx
+- !!merge <<: *mlx
+  name: "cpu-mlx-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-mlx"
+  mirrors:
+    - localai/localai-backends:master-cpu-mlx
+- !!merge <<: *mlx
+  name: "cuda12-mlx"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx
+- !!merge <<: *mlx
+  name: "cuda12-mlx-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-mlx
+- !!merge <<: *mlx
+  name: "cuda13-mlx"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx
+- !!merge <<: *mlx
+  name: "cuda13-mlx-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-mlx
+- !!merge <<: *mlx
+  name: "nvidia-l4t-mlx"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-mlx
+- !!merge <<: *mlx
+  name: "nvidia-l4t-mlx-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-mlx
+- !!merge <<: *mlx
+  name: "cuda13-nvidia-l4t-arm64-mlx"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx
+- !!merge <<: *mlx
+  name: "cuda13-nvidia-l4t-arm64-mlx-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx
+## mlx-vlm
+- !!merge <<: *mlx-vlm
+  name: "cpu-mlx-vlm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-mlx-vlm"
+  mirrors:
+    - localai/localai-backends:latest-cpu-mlx-vlm
+- !!merge <<: *mlx-vlm
+  name: "cpu-mlx-vlm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-mlx-vlm"
+  mirrors:
+    - localai/localai-backends:master-cpu-mlx-vlm
+- !!merge <<: *mlx-vlm
+  name: "cuda12-mlx-vlm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx-vlm"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx-vlm
+- !!merge <<: *mlx-vlm
+  name: "cuda12-mlx-vlm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx-vlm"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-mlx-vlm
+- !!merge <<: *mlx-vlm
+  name: "cuda13-mlx-vlm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx-vlm"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx-vlm
+- !!merge <<: *mlx-vlm
+  name: "cuda13-mlx-vlm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx-vlm"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-mlx-vlm
+- !!merge <<: *mlx-vlm
+  name: "nvidia-l4t-mlx-vlm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx-vlm"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-mlx-vlm
+- !!merge <<: *mlx-vlm
+  name: "nvidia-l4t-mlx-vlm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx-vlm"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-mlx-vlm
+- !!merge <<: *mlx-vlm
+  name: "cuda13-nvidia-l4t-arm64-mlx-vlm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-vlm"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-vlm
+- !!merge <<: *mlx-vlm
+  name: "cuda13-nvidia-l4t-arm64-mlx-vlm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-vlm"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-vlm
+## mlx-audio
+- !!merge <<: *mlx-audio
+  name: "cpu-mlx-audio"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-mlx-audio"
+  mirrors:
+    - localai/localai-backends:latest-cpu-mlx-audio
+- !!merge <<: *mlx-audio
+  name: "cpu-mlx-audio-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-mlx-audio"
+  mirrors:
+    - localai/localai-backends:master-cpu-mlx-audio
+- !!merge <<: *mlx-audio
+  name: "cuda12-mlx-audio"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx-audio"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx-audio
+- !!merge <<: *mlx-audio
+  name: "cuda12-mlx-audio-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx-audio"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-mlx-audio
+- !!merge <<: *mlx-audio
+  name: "cuda13-mlx-audio"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx-audio"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx-audio
+- !!merge <<: *mlx-audio
+  name: "cuda13-mlx-audio-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx-audio"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-mlx-audio
+- !!merge <<: *mlx-audio
+  name: "nvidia-l4t-mlx-audio"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx-audio"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-mlx-audio
+- !!merge <<: *mlx-audio
+  name: "nvidia-l4t-mlx-audio-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx-audio"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-mlx-audio
+- !!merge <<: *mlx-audio
+  name: "cuda13-nvidia-l4t-arm64-mlx-audio"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-audio"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-audio
+- !!merge <<: *mlx-audio
+  name: "cuda13-nvidia-l4t-arm64-mlx-audio-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-audio"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-audio
 - !!merge <<: *kitten-tts
   name: "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: "metal-kitten-tts"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-kitten-tts"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-kitten-tts
+- !!merge <<: *kitten-tts
+  name: "metal-kitten-tts-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-kitten-tts"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-kitten-tts
 - !!merge <<: *huggingface
   name: "huggingface-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-huggingface"
   mirrors:
     - localai/localai-backends:master-huggingface
+- !!merge <<: *huggingface
+  name: "metal-huggingface"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-huggingface"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-huggingface
+- !!merge <<: *huggingface
+  name: "metal-huggingface-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-huggingface"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-huggingface
 - !!merge <<: *local-store
   name: "local-store-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-cpu-local-store"
   mirrors:
     - localai/localai-backends:master-cpu-local-store
+- !!merge <<: *local-store
+  name: "metal-local-store"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-local-store"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-local-store
+- !!merge <<: *local-store
+  name: "metal-local-store-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-local-store"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-local-store
 - !!merge <<: *silero-vad
   name: "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: "metal-silero-vad"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-silero-vad"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-silero-vad
+- !!merge <<: *silero-vad
+  name: "metal-silero-vad-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-silero-vad"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-silero-vad
 - !!merge <<: *piper
   name: "piper-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-piper"
   mirrors:
     - localai/localai-backends:master-piper
+- !!merge <<: *piper
+  name: "metal-piper"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-piper"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-piper
+- !!merge <<: *piper
+  name: "metal-piper-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-piper"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-piper
 ## llama-cpp
 - !!merge <<: *llamacpp
   name: "nvidia-l4t-arm64-llama-cpp"
@@ -1048,6 +1338,7 @@
     intel: "intel-rfdetr-development"
     #amd: "rocm-rfdetr-development"
     nvidia-l4t: "nvidia-l4t-arm64-rfdetr-development"
+    metal: "metal-rfdetr-development"
     default: "cpu-rfdetr-development"
     nvidia-cuda-13: "cuda13-rfdetr-development"
 - !!merge <<: *rfdetr
@@ -1115,6 +1406,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-rfdetr"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-rfdetr
+- !!merge <<: *rfdetr
+  name: "metal-rfdetr"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-rfdetr"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-rfdetr
+- !!merge <<: *rfdetr
+  name: "metal-rfdetr-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-rfdetr"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-rfdetr
 ## Rerankers
 - !!merge <<: *rerankers
   name: "rerankers-development"
@@ -1122,6 +1423,7 @@
     nvidia: "cuda12-rerankers-development"
     intel: "intel-rerankers-development"
     amd: "rocm-rerankers-development"
+    metal: "metal-rerankers-development"
     nvidia-cuda-13: "cuda13-rerankers-development"
 - !!merge <<: *rerankers
   name: "cuda12-rerankers"
@@ -1163,6 +1465,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-rerankers"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-rerankers
+- !!merge <<: *rerankers
+  name: "metal-rerankers"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-rerankers"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-rerankers
+- !!merge <<: *rerankers
+  name: "metal-rerankers-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-rerankers"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-rerankers
 ## Transformers
 - !!merge <<: *transformers
   name: "transformers-development"
@@ -1170,6 +1482,7 @@
     nvidia: "cuda12-transformers-development"
     intel: "intel-transformers-development"
     amd: "rocm-transformers-development"
+    metal: "metal-transformers-development"
     nvidia-cuda-13: "cuda13-transformers-development"
 - !!merge <<: *transformers
   name: "cuda12-transformers"
@@ -1211,6 +1524,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-transformers"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-transformers
+- !!merge <<: *transformers
+  name: "metal-transformers"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-transformers"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-transformers
+- !!merge <<: *transformers
+  name: "metal-transformers-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-transformers"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-transformers
 ## Diffusers
 - !!merge <<: *diffusers
   name: "diffusers-development"
@@ -1302,6 +1625,77 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-diffusers"
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-diffusers
+## ace-step
+- !!merge <<: *ace-step
+  name: "cpu-ace-step"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-ace-step"
+  mirrors:
+    - localai/localai-backends:latest-cpu-ace-step
+- !!merge <<: *ace-step
+  name: "cpu-ace-step-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-ace-step"
+  mirrors:
+    - localai/localai-backends:master-cpu-ace-step
+- !!merge <<: *ace-step
+  name: "cuda12-ace-step"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-ace-step"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-ace-step
+- !!merge <<: *ace-step
+  name: "cuda12-ace-step-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-ace-step"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-ace-step
+- !!merge <<: *ace-step
+  name: "cuda13-ace-step"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-ace-step"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-ace-step
+- !!merge <<: *ace-step
+  name: "cuda13-ace-step-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-ace-step"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-ace-step
+- !!merge <<: *ace-step
+  name: "rocm-ace-step"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-ace-step"
+  mirrors:
+    - localai/localai-backends:latest-gpu-rocm-hipblas-ace-step
+- !!merge <<: *ace-step
+  name: "rocm-ace-step-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-ace-step"
+  mirrors:
+    - localai/localai-backends:master-gpu-rocm-hipblas-ace-step
+- !!merge <<: *ace-step
+  name: "intel-ace-step"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-ace-step"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-ace-step
+- !!merge <<: *ace-step
+  name: "intel-ace-step-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-ace-step"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-ace-step
+- !!merge <<: *ace-step
+  name: "metal-ace-step"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-ace-step"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-ace-step
+- !!merge <<: *ace-step
+  name: "metal-ace-step-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-ace-step"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-ace-step
+- !!merge <<: *ace-step
+  name: "nvidia-l4t-ace-step"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-ace-step"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-ace-step
+- !!merge <<: *ace-step
+  name: "nvidia-l4t-ace-step-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-ace-step"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-ace-step
 ## kokoro
 - !!merge <<: *kokoro
   name: "kokoro-development"
@@ -1310,6 +1704,7 @@
     intel: "intel-kokoro-development"
     amd: "rocm-kokoro-development"
     nvidia-l4t: "nvidia-l4t-kokoro-development"
+    metal: "metal-kokoro-development"
 - !!merge <<: *kokoro
   name: "cuda12-kokoro-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-kokoro"
@@ -1360,6 +1755,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-kokoro"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-kokoro
+- !!merge <<: *kokoro
+  name: "metal-kokoro"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-kokoro"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-kokoro
+- !!merge <<: *kokoro
+  name: "metal-kokoro-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-kokoro"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-kokoro
 ## faster-whisper
 - !!merge <<: *faster-whisper
   name: "faster-whisper-development"
@@ -1367,6 +1772,7 @@
     nvidia: "cuda12-faster-whisper-development"
     intel: "intel-faster-whisper-development"
     amd: "rocm-faster-whisper-development"
+    metal: "metal-faster-whisper-development"
     nvidia-cuda-13: "cuda13-faster-whisper-development"
 - !!merge <<: *faster-whisper
   name: "cuda12-faster-whisper-development"
@@ -1398,6 +1804,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-faster-whisper"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-faster-whisper
+- !!merge <<: *faster-whisper
+  name: "metal-faster-whisper"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-faster-whisper"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-faster-whisper
+- !!merge <<: *faster-whisper
+  name: "metal-faster-whisper-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-faster-whisper"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-faster-whisper
 ## moonshine
 - !!merge <<: *moonshine
   name: "moonshine-development"
@@ -1436,12 +1852,23 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-moonshine"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-moonshine
+- !!merge <<: *moonshine
+  name: "metal-moonshine"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-moonshine"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-moonshine
+- !!merge <<: *moonshine
+  name: "metal-moonshine-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-moonshine"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-moonshine
 ## whisperx
 - !!merge <<: *whisperx
   name: "whisperx-development"
   capabilities:
     nvidia: "cuda12-whisperx-development"
     amd: "rocm-whisperx-development"
+    metal: "metal-whisperx-development"
     default: "cpu-whisperx-development"
     nvidia-cuda-13: "cuda13-whisperx-development"
     nvidia-cuda-12: "cuda12-whisperx-development"
@@ -1485,6 +1912,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-whisperx"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-whisperx
+- !!merge <<: *whisperx
+  name: "metal-whisperx"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-whisperx"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-whisperx
+- !!merge <<: *whisperx
+  name: "metal-whisperx-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-whisperx"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-whisperx
 ## coqui
 
 - !!merge <<: *coqui
@@ -1493,6 +1930,7 @@
     nvidia: "cuda12-coqui-development"
     intel: "intel-coqui-development"
     amd: "rocm-coqui-development"
+    metal: "metal-coqui-development"
 - !!merge <<: *coqui
   name: "cuda12-coqui"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-coqui"
@@ -1523,6 +1961,42 @@
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-coqui"
   mirrors:
     - localai/localai-backends:latest-gpu-rocm-hipblas-coqui
+- !!merge <<: *coqui
+  name: "metal-coqui"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-coqui"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-coqui
+- !!merge <<: *coqui
+  name: "metal-coqui-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-coqui"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-coqui
+## outetts
+- !!merge <<: *outetts
+  name: "outetts-development"
+  capabilities:
+    default: "cpu-outetts-development"
+    nvidia-cuda-12: "cuda12-outetts-development"
+- !!merge <<: *outetts
+  name: "cpu-outetts"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-outetts"
+  mirrors:
+    - localai/localai-backends:latest-cpu-outetts
+- !!merge <<: *outetts
+  name: "cpu-outetts-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-outetts"
+  mirrors:
+    - localai/localai-backends:master-cpu-outetts
+- !!merge <<: *outetts
+  name: "cuda12-outetts"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-outetts"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-outetts
+- !!merge <<: *outetts
+  name: "cuda12-outetts-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-outetts"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-outetts
 ## chatterbox
 - !!merge <<: *chatterbox
   name: "chatterbox-development"
@@ -1603,6 +2077,7 @@
     intel: "intel-vibevoice-development"
     amd: "rocm-vibevoice-development"
     nvidia-l4t: "nvidia-l4t-vibevoice-development"
+    metal: "metal-vibevoice-development"
     default: "cpu-vibevoice-development"
     nvidia-cuda-13: "cuda13-vibevoice-development"
     nvidia-cuda-12: "cuda12-vibevoice-development"
@@ -1678,6 +2153,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-vibevoice"
   mirrors:
     - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-vibevoice
+- !!merge <<: *vibevoice
+  name: "metal-vibevoice"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-vibevoice"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-vibevoice
+- !!merge <<: *vibevoice
+  name: "metal-vibevoice-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-vibevoice"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-vibevoice
 ## qwen-tts
 - !!merge <<: *qwen-tts
   name: "qwen-tts-development"
@@ -1686,6 +2171,7 @@
     intel: "intel-qwen-tts-development"
     amd: "rocm-qwen-tts-development"
     nvidia-l4t: "nvidia-l4t-qwen-tts-development"
+    metal: "metal-qwen-tts-development"
     default: "cpu-qwen-tts-development"
     nvidia-cuda-13: "cuda13-qwen-tts-development"
     nvidia-cuda-12: "cuda12-qwen-tts-development"
@@ -1761,6 +2247,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-tts"
   mirrors:
     - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "metal-qwen-tts"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-qwen-tts"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "metal-qwen-tts-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-qwen-tts"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-qwen-tts
 ## qwen-asr
 - !!merge <<: *qwen-asr
   name: "qwen-asr-development"
@@ -1769,6 +2265,7 @@
     intel: "intel-qwen-asr-development"
     amd: "rocm-qwen-asr-development"
     nvidia-l4t: "nvidia-l4t-qwen-asr-development"
+    metal: "metal-qwen-asr-development"
     default: "cpu-qwen-asr-development"
     nvidia-cuda-13: "cuda13-qwen-asr-development"
     nvidia-cuda-12: "cuda12-qwen-asr-development"
@@ -1844,6 +2341,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-asr"
   mirrors:
     - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-asr
+- !!merge <<: *qwen-asr
+  name: "metal-qwen-asr"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-qwen-asr"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-qwen-asr
+- !!merge <<: *qwen-asr
+  name: "metal-qwen-asr-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-qwen-asr"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-qwen-asr
 ## voxcpm
 - !!merge <<: *voxcpm
   name: "voxcpm-development"
@@ -1851,6 +2358,7 @@
     nvidia: "cuda12-voxcpm-development"
     intel: "intel-voxcpm-development"
     amd: "rocm-voxcpm-development"
+    metal: "metal-voxcpm-development"
     default: "cpu-voxcpm-development"
     nvidia-cuda-13: "cuda13-voxcpm-development"
     nvidia-cuda-12: "cuda12-voxcpm-development"
@@ -1904,6 +2412,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-voxcpm"
   mirrors:
     - localai/localai-backends:master-gpu-rocm-hipblas-voxcpm
+- !!merge <<: *voxcpm
+  name: "metal-voxcpm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-voxcpm"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-voxcpm
+- !!merge <<: *voxcpm
+  name: "metal-voxcpm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-voxcpm"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-voxcpm
 ## pocket-tts
 - !!merge <<: *pocket-tts
   name: "pocket-tts-development"
@@ -1912,6 +2430,7 @@
     intel: "intel-pocket-tts-development"
     amd: "rocm-pocket-tts-development"
     nvidia-l4t: "nvidia-l4t-pocket-tts-development"
+    metal: "metal-pocket-tts-development"
     default: "cpu-pocket-tts-development"
     nvidia-cuda-13: "cuda13-pocket-tts-development"
     nvidia-cuda-12: "cuda12-pocket-tts-development"
@@ -1987,3 +2506,13 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-pocket-tts"
   mirrors:
     - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-pocket-tts
+- !!merge <<: *pocket-tts
+  name: "metal-pocket-tts"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-pocket-tts"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-pocket-tts
+- !!merge <<: *pocket-tts
+  name: "metal-pocket-tts-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-pocket-tts"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-pocket-tts

backend/python/ace-step/Makefile

@@ -0,0 +1,16 @@
+.DEFAULT_GOAL := install
+
+.PHONY: install
+install:
+	bash install.sh
+
+.PHONY: protogen-clean
+protogen-clean:
+	$(RM) backend_pb2_grpc.py backend_pb2.py
+
+.PHONY: clean
+clean: protogen-clean
+	rm -rf venv __pycache__
+
+test: install
+	bash test.sh

backend/python/ace-step/backend.py

@@ -0,0 +1,472 @@
+#!/usr/bin/env python3
+"""
+LocalAI ACE-Step Backend
+
+gRPC backend for ACE-Step 1.5 music generation. Aligns with upstream acestep API:
+- LoadModel: initializes AceStepHandler (DiT) and LLMHandler, parses Options.
+- SoundGeneration: uses create_sample (simple mode), format_sample (optional), then
+  generate_music from acestep.inference. Writes first output to request.dst.
+- Fail hard: no fallback WAV on error; exceptions propagate to gRPC.
+"""
+from concurrent import futures
+import argparse
+import shutil
+import signal
+import sys
+import os
+import tempfile
+
+import backend_pb2
+import backend_pb2_grpc
+import grpc
+from acestep.inference import (
+    GenerationParams,
+    GenerationConfig,
+    generate_music,
+    create_sample,
+    format_sample,
+)
+from acestep.handler import AceStepHandler
+from acestep.llm_inference import LLMHandler
+from acestep.model_downloader import ensure_lm_model
+
+
+_ONE_DAY_IN_SECONDS = 60 * 60 * 24
+MAX_WORKERS = int(os.environ.get("PYTHON_GRPC_MAX_WORKERS", "1"))
+
+# Model name -> HuggingFace/ModelScope repo (from upstream api_server.py)
+MODEL_REPO_MAPPING = {
+    "acestep-v15-turbo": "ACE-Step/Ace-Step1.5",
+    "acestep-5Hz-lm-0.6B": "ACE-Step/Ace-Step1.5",
+    "acestep-5Hz-lm-1.7B": "ACE-Step/Ace-Step1.5",
+    "vae": "ACE-Step/Ace-Step1.5",
+    "Qwen3-Embedding-0.6B": "ACE-Step/Ace-Step1.5",
+    "acestep-v15-base": "ACE-Step/acestep-v15-base",
+    "acestep-v15-sft": "ACE-Step/acestep-v15-sft",
+    "acestep-v15-turbo-shift3": "ACE-Step/acestep-v15-turbo-shift3",
+    "acestep-5Hz-lm-4B": "ACE-Step/acestep-5Hz-lm-4B",
+}
+DEFAULT_REPO_ID = "ACE-Step/Ace-Step1.5"
+
+def _is_float(s):
+    try:
+        float(s)
+        return True
+    except (ValueError, TypeError):
+        return False
+
+
+def _is_int(s):
+    try:
+        int(s)
+        return True
+    except (ValueError, TypeError):
+        return False
+
+
+def _parse_timesteps(s):
+    if s is None or (isinstance(s, str) and not s.strip()):
+        return None
+    if isinstance(s, (list, tuple)):
+        return [float(x) for x in s]
+    try:
+        return [float(x.strip()) for x in str(s).split(",") if x.strip()]
+    except (ValueError, TypeError):
+        return None
+
+
+def _parse_options(opts_list):
+    """Parse repeated 'key:value' options into a dict. Coerce numeric and bool."""
+    out = {}
+    for opt in opts_list or []:
+        if ":" not in opt:
+            continue
+        key, value = opt.split(":", 1)
+        key = key.strip()
+        value = value.strip()
+        if _is_int(value):
+            out[key] = int(value)
+        elif _is_float(value):
+            out[key] = float(value)
+        elif value.lower() in ("true", "false"):
+            out[key] = value.lower() == "true"
+        else:
+            out[key] = value
+    return out
+
+
+def _generate_audio_sync(servicer, payload, dst_path):
+    """
+    Run full ACE-Step pipeline using acestep.inference:
+    - If sample_mode/sample_query: create_sample() for caption/lyrics/metadata.
+    - If use_format and caption/lyrics: format_sample().
+    - Build GenerationParams and GenerationConfig, then generate_music().
+    Writes the first generated audio to dst_path. Raises on failure.
+    """
+
+    opts = servicer.options
+    dit_handler = servicer.dit_handler
+    llm_handler = servicer.llm_handler
+
+    for key, value in opts.items():
+        if key not in payload:
+            payload[key] = value
+
+    def _opt(name, default):
+        return opts.get(name, default)
+
+    lm_temperature = _opt("temperature", 0.85)
+    lm_cfg_scale = _opt("lm_cfg_scale", _opt("cfg_scale", 2.0))
+    lm_top_k = opts.get("top_k")
+    lm_top_p = _opt("top_p", 0.9)
+    if lm_top_p is not None and lm_top_p >= 1.0:
+        lm_top_p = None
+    inference_steps = _opt("inference_steps", 8)
+    guidance_scale = _opt("guidance_scale", 7.0)
+    batch_size = max(1, int(_opt("batch_size", 1)))
+
+    use_simple = bool(payload.get("sample_query") or payload.get("text"))
+    sample_mode = use_simple and (payload.get("thinking") or payload.get("sample_mode"))
+    sample_query = (payload.get("sample_query") or payload.get("text") or "").strip()
+    use_format = bool(payload.get("use_format"))
+    caption = (payload.get("prompt") or payload.get("caption") or "").strip()
+    lyrics = (payload.get("lyrics") or "").strip()
+    vocal_language = (payload.get("vocal_language") or "en").strip()
+    instrumental = bool(payload.get("instrumental"))
+    bpm = payload.get("bpm")
+    key_scale = (payload.get("key_scale") or "").strip()
+    time_signature = (payload.get("time_signature") or "").strip()
+    audio_duration = payload.get("audio_duration")
+    if audio_duration is not None:
+        try:
+            audio_duration = float(audio_duration)
+        except (TypeError, ValueError):
+            audio_duration = None
+
+    if sample_mode and llm_handler and getattr(llm_handler, "llm_initialized", False):
+        parsed_language = None
+        if sample_query:
+            for hint in ("english", "en", "chinese", "zh", "japanese", "ja"):
+                if hint in sample_query.lower():
+                    parsed_language = "en" if hint == "english" or hint == "en" else hint
+                    break
+        vocal_lang = vocal_language if vocal_language and vocal_language != "unknown" else parsed_language
+        sample_result = create_sample(
+            llm_handler=llm_handler,
+            query=sample_query or "NO USER INPUT",
+            instrumental=instrumental,
+            vocal_language=vocal_lang,
+            temperature=lm_temperature,
+            top_k=lm_top_k,
+            top_p=lm_top_p,
+            use_constrained_decoding=True,
+        )
+        if not sample_result.success:
+            raise RuntimeError(f"create_sample failed: {sample_result.error or sample_result.status_message}")
+        caption = sample_result.caption or caption
+        lyrics = sample_result.lyrics or lyrics
+        bpm = sample_result.bpm
+        key_scale = sample_result.keyscale or key_scale
+        time_signature = sample_result.timesignature or time_signature
+        if sample_result.duration is not None:
+            audio_duration = sample_result.duration
+        if getattr(sample_result, "language", None):
+            vocal_language = sample_result.language
+
+    if use_format and (caption or lyrics) and llm_handler and getattr(llm_handler, "llm_initialized", False):
+        user_metadata = {}
+        if bpm is not None:
+            user_metadata["bpm"] = bpm
+        if audio_duration is not None and float(audio_duration) > 0:
+            user_metadata["duration"] = int(audio_duration)
+        if key_scale:
+            user_metadata["keyscale"] = key_scale
+        if time_signature:
+            user_metadata["timesignature"] = time_signature
+        if vocal_language and vocal_language != "unknown":
+            user_metadata["language"] = vocal_language
+        format_result = format_sample(
+            llm_handler=llm_handler,
+            caption=caption,
+            lyrics=lyrics,
+            user_metadata=user_metadata if user_metadata else None,
+            temperature=lm_temperature,
+            top_k=lm_top_k,
+            top_p=lm_top_p,
+            use_constrained_decoding=True,
+        )
+        if format_result.success:
+            caption = format_result.caption or caption
+            lyrics = format_result.lyrics or lyrics
+            if format_result.duration is not None:
+                audio_duration = format_result.duration
+            if format_result.bpm is not None:
+                bpm = format_result.bpm
+            if format_result.keyscale:
+                key_scale = format_result.keyscale
+            if format_result.timesignature:
+                time_signature = format_result.timesignature
+            if getattr(format_result, "language", None):
+                vocal_language = format_result.language
+
+    thinking = bool(payload.get("thinking"))
+    use_cot_metas = not sample_mode
+    params = GenerationParams(
+        task_type=payload.get("task_type", "text2music"),
+        instruction=payload.get("instruction", "Fill the audio semantic mask based on the given conditions:"),
+        reference_audio=payload.get("reference_audio_path"),
+        src_audio=payload.get("src_audio_path"),
+        audio_codes=payload.get("audio_code_string", ""),
+        caption=caption,
+        lyrics=lyrics,
+        instrumental=instrumental or (not lyrics or str(lyrics).strip().lower() in ("[inst]", "[instrumental]")),
+        vocal_language=vocal_language or "unknown",
+        bpm=bpm,
+        keyscale=key_scale,
+        timesignature=time_signature,
+        duration=float(audio_duration) if audio_duration and float(audio_duration) > 0 else -1.0,
+        inference_steps=inference_steps,
+        seed=int(payload.get("seed", -1)),
+        guidance_scale=guidance_scale,
+        use_adg=bool(payload.get("use_adg")),
+        cfg_interval_start=float(payload.get("cfg_interval_start", 0.0)),
+        cfg_interval_end=float(payload.get("cfg_interval_end", 1.0)),
+        shift=float(payload.get("shift", 1.0)),
+        infer_method=(payload.get("infer_method") or "ode").strip(),
+        timesteps=_parse_timesteps(payload.get("timesteps")),
+        repainting_start=float(payload.get("repainting_start", 0.0)),
+        repainting_end=float(payload.get("repainting_end", -1)) if payload.get("repainting_end") is not None else -1,
+        audio_cover_strength=float(payload.get("audio_cover_strength", 1.0)),
+        thinking=thinking,
+        lm_temperature=lm_temperature,
+        lm_cfg_scale=lm_cfg_scale,
+        lm_top_k=lm_top_k or 0,
+        lm_top_p=lm_top_p if lm_top_p is not None and lm_top_p < 1.0 else 0.9,
+        lm_negative_prompt=payload.get("lm_negative_prompt", "NO USER INPUT"),
+        use_cot_metas=use_cot_metas,
+        use_cot_caption=bool(payload.get("use_cot_caption", True)),
+        use_cot_language=bool(payload.get("use_cot_language", True)),
+        use_constrained_decoding=True,
+    )
+
+    config = GenerationConfig(
+        batch_size=batch_size,
+        allow_lm_batch=bool(payload.get("allow_lm_batch", False)),
+        use_random_seed=bool(payload.get("use_random_seed", True)),
+        seeds=payload.get("seeds"),
+        lm_batch_chunk_size=max(1, int(payload.get("lm_batch_chunk_size", 8))),
+        constrained_decoding_debug=bool(payload.get("constrained_decoding_debug")),
+        audio_format=(payload.get("audio_format") or "flac").strip() or "flac",
+    )
+
+    save_dir = tempfile.mkdtemp(prefix="ace_step_")
+    try:
+        result = generate_music(
+            dit_handler=dit_handler,
+            llm_handler=llm_handler if (llm_handler and getattr(llm_handler, "llm_initialized", False)) else None,
+            params=params,
+            config=config,
+            save_dir=save_dir,
+            progress=None,
+        )
+        if not result.success:
+            raise RuntimeError(result.error or result.status_message or "generate_music failed")
+
+        audios = result.audios or []
+        if not audios:
+            raise RuntimeError("generate_music returned no audio")
+
+        first_path = audios[0].get("path") or ""
+        if not first_path or not os.path.isfile(first_path):
+            raise RuntimeError("first generated audio path missing or not a file")
+
+        shutil.copy2(first_path, dst_path)
+    finally:
+        try:
+            shutil.rmtree(save_dir, ignore_errors=True)
+        except Exception:
+            pass
+
+
+class BackendServicer(backend_pb2_grpc.BackendServicer):
+    def __init__(self):
+        self.model_path = None
+        self.model_dir = None
+        self.checkpoint_dir = None
+        self.project_root = None
+        self.options = {}
+        self.dit_handler = None
+        self.llm_handler = None
+
+    def Health(self, request, context):
+        return backend_pb2.Reply(message=b"OK")
+
+    def LoadModel(self, request, context):
+        try:
+            self.options = _parse_options(list(getattr(request, "Options", []) or []))
+            model_path = getattr(request, "ModelPath", None) or ""
+            model_name = (request.Model or "").strip()
+            model_file = (getattr(request, "ModelFile", None) or "").strip()
+
+            # Model dir: where we store checkpoints (always under LocalAI models path, never backend dir)
+            if model_path and model_name:
+                model_dir = os.path.join(model_path, model_name)
+            elif model_file:
+                model_dir = model_file
+            else:
+                model_dir = os.path.abspath(model_name or ".")
+            self.model_dir = model_dir
+            self.checkpoint_dir = os.path.join(model_dir, "checkpoints")
+            self.project_root = model_dir
+            self.model_path = os.path.join(self.checkpoint_dir, model_name or os.path.basename(model_dir.rstrip("/\\")))
+
+            config_path = model_name or os.path.basename(model_dir.rstrip("/\\"))
+            os.makedirs(self.checkpoint_dir, exist_ok=True)
+
+            self.dit_handler = AceStepHandler()
+            # Patch handler so it uses our model dir instead of site-packages/checkpoints
+            self.dit_handler._get_project_root = lambda: self.project_root
+            device = self.options.get("device", "auto")
+            use_flash = self.options.get("use_flash_attention", True)
+            if isinstance(use_flash, str):
+                use_flash = str(use_flash).lower() in ("1", "true", "yes")
+            offload = self.options.get("offload_to_cpu", False)
+            if isinstance(offload, str):
+                offload = str(offload).lower() in ("1", "true", "yes")
+            status_msg, ok = self.dit_handler.initialize_service(
+                project_root=self.project_root,
+                config_path=config_path,
+                device=device,
+                use_flash_attention=use_flash,
+                compile_model=False,
+                offload_to_cpu=offload,
+                offload_dit_to_cpu=bool(self.options.get("offload_dit_to_cpu", False)),
+            )
+            if not ok:
+                return backend_pb2.Result(success=False, message=f"DiT init failed: {status_msg}")
+
+            self.llm_handler = None
+            if self.options.get("init_lm", True):
+                lm_model = self.options.get("lm_model_path", "acestep-5Hz-lm-0.6B")
+                
+                # Ensure LM model is downloaded before initializing
+                try:
+                    from pathlib import Path
+                    lm_success, lm_msg = ensure_lm_model(
+                        model_name=lm_model,
+                        checkpoints_dir=Path(self.checkpoint_dir),
+                        prefer_source=None,  # Auto-detect HuggingFace vs ModelScope
+                    )
+                    if not lm_success:
+                        print(f"[ace-step] Warning: LM model download failed: {lm_msg}", file=sys.stderr)
+                        # Continue anyway - LLM initialization will fail gracefully
+                    else:
+                        print(f"[ace-step] LM model ready: {lm_msg}", file=sys.stderr)
+                except Exception as e:
+                    print(f"[ace-step] Warning: LM model download check failed: {e}", file=sys.stderr)
+                    # Continue anyway - LLM initialization will fail gracefully
+                
+                self.llm_handler = LLMHandler()
+                lm_backend = (self.options.get("lm_backend") or "vllm").strip().lower()
+                if lm_backend not in ("vllm", "pt"):
+                    lm_backend = "vllm"
+                lm_status, lm_ok = self.llm_handler.initialize(
+                    checkpoint_dir=self.checkpoint_dir,
+                    lm_model_path=lm_model,
+                    backend=lm_backend,
+                    device=device,
+                    offload_to_cpu=offload,
+                    dtype=getattr(self.dit_handler, "dtype", None),
+                )
+                if not lm_ok:
+                    self.llm_handler = None
+                    print(f"[ace-step] LM init failed (optional): {lm_status}", file=sys.stderr)
+
+            print(f"[ace-step] LoadModel: model={self.model_path}, options={list(self.options.keys())}", file=sys.stderr)
+            return backend_pb2.Result(success=True, message="Model loaded successfully")
+        except Exception as err:
+            return backend_pb2.Result(success=False, message=f"LoadModel error: {err}")
+
+    def SoundGeneration(self, request, context):
+        if not request.dst:
+            return backend_pb2.Result(success=False, message="request.dst is required")
+
+        use_simple = bool(request.text)
+        if use_simple:
+            payload = {
+                "sample_query": request.text or "",
+                "sample_mode": True,
+                "thinking": True,
+                "vocal_language": request.language or request.GetLanguage() or "en",
+                "instrumental": request.instrumental if request.HasField("instrumental") else False,
+            }
+        else:
+            caption = request.caption or request.GetCaption() or request.text
+            payload = {
+                "prompt": caption,
+                "lyrics": request.lyrics or request.lyrics or "",
+                "thinking": request.think if request.HasField("think") else False,
+                "vocal_language": request.language or request.GetLanguage() or "en",
+            }
+            if request.HasField("bpm"):
+                payload["bpm"] = request.bpm
+            if request.HasField("keyscale") and request.keyscale:
+                payload["key_scale"] = request.keyscale
+            if request.HasField("timesignature") and request.timesignature:
+                payload["time_signature"] = request.timesignature
+            if request.HasField("duration") and request.duration:
+                payload["audio_duration"] = int(request.duration) if request.duration else None
+            if request.src:
+                payload["src_audio_path"] = request.src
+
+        _generate_audio_sync(self, payload, request.dst)
+        return backend_pb2.Result(success=True, message="Sound generated successfully")
+
+    def TTS(self, request, context):
+        if not request.dst:
+            return backend_pb2.Result(success=False, message="request.dst is required")
+        payload = {
+            "sample_query": request.text,
+            "sample_mode": True,
+            "thinking": False,
+            "vocal_language": (request.language if request.language else "") or "en",
+            "instrumental": False,
+        }
+        _generate_audio_sync(self, payload, request.dst)
+        return backend_pb2.Result(success=True, message="TTS (music fallback) generated successfully")
+
+
+def serve(address):
+    server = grpc.server(
+        futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
+        options=[
+            ("grpc.max_message_length", 50 * 1024 * 1024),
+            ("grpc.max_send_message_length", 50 * 1024 * 1024),
+            ("grpc.max_receive_message_length", 50 * 1024 * 1024),
+        ],
+    )
+    backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
+    server.add_insecure_port(address)
+    server.start()
+    print(f"[ace-step] Server listening on {address}", file=sys.stderr)
+
+    def shutdown(sig, frame):
+        server.stop(0)
+        sys.exit(0)
+
+    signal.signal(signal.SIGINT, shutdown)
+    signal.signal(signal.SIGTERM, shutdown)
+
+    try:
+        while True:
+            import time
+            time.sleep(_ONE_DAY_IN_SECONDS)
+    except KeyboardInterrupt:
+        server.stop(0)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--addr", default="localhost:50051", help="Listen address")
+    args = parser.parse_args()
+    serve(args.addr)

backend/python/ace-step/install.sh

@@ -0,0 +1,26 @@
+#!/bin/bash
+set -e
+
+backend_dir=$(dirname $0)
+if [ -d $backend_dir/common ]; then
+    source $backend_dir/common/libbackend.sh
+else
+    source $backend_dir/../common/libbackend.sh
+fi
+
+PYTHON_VERSION="3.11"
+PYTHON_PATCH="14"
+PY_STANDALONE_TAG="20260203"
+
+installRequirements
+
+if [ ! -d ACE-Step-1.5 ]; then
+    git clone https://github.com/ace-step/ACE-Step-1.5
+    cd ACE-Step-1.5/
+    if [ "x${USE_PIP}" == "xtrue" ]; then
+        pip install ${EXTRA_PIP_INSTALL_FLAGS:-} --no-deps .
+    else
+        uv pip install ${EXTRA_PIP_INSTALL_FLAGS:-} --no-deps .
+    fi
+fi
+

backend/python/ace-step/requirements-cpu.txt

@@ -0,0 +1,22 @@
+--extra-index-url https://download.pytorch.org/whl/cpu
+torch
+torchaudio
+torchvision
+
+# Core dependencies
+transformers>=4.51.0,<4.58.0
+diffusers
+gradio
+matplotlib>=3.7.5
+scipy>=1.10.1
+soundfile>=0.13.1
+loguru>=0.7.3
+einops>=0.8.1
+accelerate>=1.12.0
+fastapi>=0.110.0
+uvicorn[standard]>=0.27.0
+numba>=0.63.1
+vector-quantize-pytorch>=1.27.15
+torchcodec>=0.9.1
+torchao
+modelscope

backend/python/ace-step/requirements-cublas12.txt

@@ -0,0 +1,30 @@
+--extra-index-url https://download.pytorch.org/whl/cu121
+torch
+torchaudio
+torchvision
+
+# Core dependencies
+transformers>=4.51.0,<4.58.0
+diffusers
+gradio>=6.5.1
+matplotlib>=3.7.5
+scipy>=1.10.1
+soundfile>=0.13.1
+loguru>=0.7.3
+einops>=0.8.1
+accelerate>=1.12.0
+fastapi>=0.110.0
+uvicorn[standard]>=0.27.0
+numba>=0.63.1
+vector-quantize-pytorch>=1.27.15
+torchcodec>=0.9.1; sys_platform != 'darwin' or platform_machine == 'arm64'
+torchao
+modelscope
+
+# LoRA Training dependencies (optional)
+peft>=0.7.0
+lightning>=2.0.0
+
+triton>=3.0.0
+flash-attn
+xxhash

backend/python/ace-step/requirements-cublas13.txt

@@ -0,0 +1,30 @@
+--extra-index-url https://download.pytorch.org/whl/cu130
+torch==2.7.1
+torchaudio==2.7.1
+torchvision
+
+# Core dependencies
+transformers>=4.51.0,<4.58.0
+diffusers
+gradio>=6.5.1
+matplotlib>=3.7.5
+scipy>=1.10.1
+soundfile>=0.13.1
+loguru>=0.7.3
+einops>=0.8.1
+accelerate>=1.12.0
+fastapi>=0.110.0
+uvicorn[standard]>=0.27.0
+numba>=0.63.1
+vector-quantize-pytorch>=1.27.15
+torchcodec>=0.9.1; sys_platform != 'darwin' or platform_machine == 'arm64'
+torchao
+modelscope
+
+# LoRA Training dependencies (optional)
+peft>=0.7.0
+lightning>=2.0.0
+
+triton>=3.0.0
+flash-attn
+xxhash

backend/python/ace-step/requirements-hipblas.txt

@@ -0,0 +1,22 @@
+--extra-index-url https://download.pytorch.org/whl/rocm6.4
+torch==2.8.0+rocm6.4
+torchaudio
+torchvision
+
+# Core dependencies
+transformers>=4.51.0,<4.58.0
+diffusers
+gradio>=6.5.1
+matplotlib>=3.7.5
+scipy>=1.10.1
+soundfile>=0.13.1
+loguru>=0.7.3
+einops>=0.8.1
+accelerate>=1.12.0
+fastapi>=0.110.0
+uvicorn[standard]>=0.27.0
+numba>=0.63.1
+vector-quantize-pytorch>=1.27.15
+torchcodec>=0.9.1; sys_platform != 'darwin' or platform_machine == 'arm64'
+torchao
+modelscope

backend/python/ace-step/requirements-intel.txt

@@ -0,0 +1,26 @@
+--extra-index-url https://download.pytorch.org/whl/xpu
+torch
+torchaudio
+torchvision
+
+# Core dependencies
+transformers>=4.51.0,<4.58.0
+diffusers
+gradio
+matplotlib>=3.7.5
+scipy>=1.10.1
+soundfile>=0.13.1
+loguru>=0.7.3
+einops>=0.8.1
+accelerate>=1.12.0
+fastapi>=0.110.0
+uvicorn[standard]>=0.27.0
+numba>=0.63.1
+vector-quantize-pytorch>=1.27.15
+torchcodec>=0.9.1
+torchao
+modelscope
+
+# LoRA Training dependencies (optional)
+peft>=0.7.0
+lightning>=2.0.0

backend/python/ace-step/requirements-l4t12.txt

@@ -0,0 +1,30 @@
+--extra-index-url https://pypi.jetson-ai-lab.io/jp6/cu129/
+torch
+torchaudio
+torchvision
+
+# Core dependencies
+transformers>=4.51.0,<4.58.0
+diffusers
+gradio>=6.5.1
+matplotlib>=3.7.5
+scipy>=1.10.1
+soundfile>=0.13.1
+loguru>=0.7.3
+einops>=0.8.1
+accelerate>=1.12.0
+fastapi>=0.110.0
+uvicorn[standard]>=0.27.0
+numba>=0.63.1
+vector-quantize-pytorch>=1.27.15
+torchcodec>=0.9.1; sys_platform != 'darwin' or platform_machine == 'arm64'
+torchao
+modelscope
+
+# LoRA Training dependencies (optional)
+peft>=0.7.0
+lightning>=2.0.0
+
+triton>=3.0.0
+#flash-attn
+xxhash

backend/python/ace-step/requirements-l4t13.txt

@@ -0,0 +1,29 @@
+--extra-index-url https://download.pytorch.org/whl/cu130
+torch
+torchaudio
+torchvision
+# Core dependencies
+transformers>=4.51.0,<4.58.0
+diffusers
+gradio>=6.5.1
+matplotlib>=3.7.5
+scipy>=1.10.1
+soundfile>=0.13.1
+loguru>=0.7.3
+einops>=0.8.1
+accelerate>=1.12.0
+fastapi>=0.110.0
+uvicorn[standard]>=0.27.0
+numba>=0.63.1
+vector-quantize-pytorch>=1.27.15
+torchcodec>=0.9.1; sys_platform != 'darwin' or platform_machine == 'arm64'
+torchao
+modelscope
+
+# LoRA Training dependencies (optional)
+peft>=0.7.0
+lightning>=2.0.0
+
+triton>=3.0.0
+#flash-attn
+xxhash

backend/python/ace-step/requirements-mps.txt

@@ -0,0 +1,25 @@
+torch
+torchaudio
+torchvision
+
+# Core dependencies
+transformers>=4.51.0,<4.58.0
+diffusers
+gradio
+matplotlib>=3.7.5
+scipy>=1.10.1
+soundfile>=0.13.1
+loguru>=0.7.3
+einops>=0.8.1
+accelerate>=1.12.0
+fastapi>=0.110.0
+uvicorn[standard]>=0.27.0
+numba>=0.63.1
+vector-quantize-pytorch>=1.27.15
+torchcodec>=0.9.1
+torchao
+modelscope
+
+# LoRA Training dependencies (optional)
+peft>=0.7.0
+lightning>=2.0.0

backend/python/ace-step/requirements.txt

@@ -0,0 +1,4 @@
+setuptools
+grpcio==1.76.0
+protobuf
+certifi

backend/python/ace-step/run.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+backend_dir=$(dirname $0)
+if [ -d $backend_dir/common ]; then
+    source $backend_dir/common/libbackend.sh
+else
+    source $backend_dir/../common/libbackend.sh
+fi
+
+startBackend $@

backend/python/ace-step/test.py

@@ -0,0 +1,53 @@
+"""
+Tests for the ACE-Step gRPC backend.
+"""
+import os
+import tempfile
+import unittest
+
+import backend_pb2
+import backend_pb2_grpc
+import grpc
+
+
+class TestACEStepBackend(unittest.TestCase):
+    """Test Health, LoadModel, and SoundGeneration (minimal; no real model required)."""
+
+    @classmethod
+    def setUpClass(cls):
+        port = os.environ.get("BACKEND_PORT", "50051")
+        cls.channel = grpc.insecure_channel(f"localhost:{port}")
+        cls.stub = backend_pb2_grpc.BackendStub(cls.channel)
+
+    @classmethod
+    def tearDownClass(cls):
+        cls.channel.close()
+
+    def test_health(self):
+        response = self.stub.Health(backend_pb2.HealthMessage())
+        self.assertEqual(response.message, b"OK")
+
+    def test_load_model(self):
+        response = self.stub.LoadModel(backend_pb2.ModelOptions(Model="ace-step-test"))
+        self.assertTrue(response.success, response.message)
+
+    def test_sound_generation_minimal(self):
+        with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as f:
+            dst = f.name
+        try:
+            req = backend_pb2.SoundGenerationRequest(
+                text="upbeat pop song",
+                model="ace-step-test",
+                dst=dst,
+            )
+            response = self.stub.SoundGeneration(req)
+            self.assertTrue(response.success, response.message)
+            self.assertTrue(os.path.exists(dst), f"Output file not created: {dst}")
+            self.assertGreater(os.path.getsize(dst), 0)
+        finally:
+            if os.path.exists(dst):
+                os.unlink(dst)
+
+
+if __name__ == "__main__":
+    unittest.main()

backend/python/ace-step/test.sh

@@ -0,0 +1,19 @@
+#!/bin/bash
+set -e
+
+backend_dir=$(dirname $0)
+if [ -d $backend_dir/common ]; then
+    source $backend_dir/common/libbackend.sh
+else
+    source $backend_dir/../common/libbackend.sh
+fi
+
+# Start backend in background (use env to avoid port conflict in parallel tests)
+export PYTHONUNBUFFERED=1
+BACKEND_PORT=${BACKEND_PORT:-50051}
+python backend.py --addr "localhost:${BACKEND_PORT}" &
+BACKEND_PID=$!
+trap "kill $BACKEND_PID 2>/dev/null || true" EXIT
+sleep 3
+export BACKEND_PORT
+runUnittests

backend/python/chatterbox/requirements-mps.txt

@@ -0,0 +1,7 @@
+torch
+torchaudio
+accelerate
+numpy>=1.24.0,<1.26.0
+transformers
+# https://github.com/mudler/LocalAI/pull/6240#issuecomment-3329518289
+chatterbox-tts@git+https://git@github.com/mudler/chatterbox.git@faster

backend/python/coqui/requirements-mps.txt

@@ -0,0 +1,4 @@
+torch==2.7.1
+transformers==4.48.3
+accelerate
+coqui-tts

backend/python/faster-whisper/requirements-mps.txt

@@ -0,0 +1,8 @@
+torch==2.7.1
+faster-whisper
+opencv-python
+accelerate
+compel
+peft
+sentencepiece
+optimum-quanto

backend/python/kitten-tts/requirements-mps.txt

@@ -0,0 +1,5 @@
+grpcio==1.71.0
+protobuf
+certifi
+packaging==24.1
+https://github.com/KittenML/KittenTTS/releases/download/0.1/kittentts-0.1.0-py3-none-any.whl

backend/python/kokoro/requirements-mps.txt

@@ -0,0 +1,5 @@
+torch==2.7.1
+transformers
+accelerate
+kokoro
+soundfile

backend/python/mlx-audio/requirements-cpu.txt

@@ -0,0 +1,2 @@
+git+https://github.com/Blaizzy/mlx-audio
+mlx[cpu]

backend/python/mlx-audio/requirements-cublas12.txt

@@ -0,0 +1,2 @@
+git+https://github.com/Blaizzy/mlx-audio
+mlx[cuda12]

backend/python/mlx-audio/requirements-cublas13.txt

@@ -0,0 +1,2 @@
+git+https://github.com/Blaizzy/mlx-audio
+mlx[cuda13]

backend/python/mlx-audio/requirements-l4t12.txt

@@ -0,0 +1,2 @@
+git+https://github.com/Blaizzy/mlx-audio
+mlx[cuda12]

backend/python/mlx-audio/requirements-l4t13.txt

@@ -0,0 +1,2 @@
+git+https://github.com/Blaizzy/mlx-audio
+mlx[cuda13]

backend/python/mlx-vlm/requirements-cpu.txt

@@ -0,0 +1,2 @@
+git+https://github.com/Blaizzy/mlx-vlm
+mlx[cpu]

backend/python/mlx-vlm/requirements-cublas12.txt

@@ -0,0 +1,2 @@
+git+https://github.com/Blaizzy/mlx-vlm
+mlx[cuda12]

backend/python/mlx-vlm/requirements-cublas13.txt

@@ -0,0 +1,2 @@
+git+https://github.com/Blaizzy/mlx-vlm
+mlx[cuda13]

backend/python/mlx-vlm/requirements-l4t12.txt

@@ -0,0 +1,2 @@
+git+https://github.com/Blaizzy/mlx-vlm
+mlx[cuda12]

backend/python/mlx-vlm/requirements-l4t13.txt

@@ -0,0 +1,2 @@
+git+https://github.com/Blaizzy/mlx-vlm
+mlx[cuda13]

backend/python/mlx/requirements-cpu.txt

@@ -0,0 +1,2 @@
+mlx-lm
+mlx[cpu]

backend/python/mlx/requirements-cublas12.txt

@@ -0,0 +1,2 @@
+mlx-lm
+mlx[cuda12]

backend/python/mlx/requirements-cublas13.txt

@@ -0,0 +1,2 @@
+mlx-lm
+mlx[cuda13]

backend/python/mlx/requirements-l4t12.txt

@@ -0,0 +1,2 @@
+mlx-lm
+mlx[cuda12]

backend/python/mlx/requirements-l4t13.txt

@@ -0,0 +1,2 @@
+mlx-lm
+mlx[cuda13]

backend/python/moonshine/requirements-mps.txt

@@ -0,0 +1,4 @@
+grpcio==1.71.0
+protobuf
+grpcio-tools
+useful-moonshine-onnx@git+https://git@github.com/moonshine-ai/moonshine.git#subdirectory=moonshine-onnx

backend/python/outetts/Makefile

@@ -0,0 +1,23 @@
+.PHONY: outetts
+outetts:
+	bash install.sh
+
+.PHONY: run
+run: outetts
+	@echo "Running outetts..."
+	bash run.sh
+	@echo "outetts run."
+
+.PHONY: test
+test: outetts
+	@echo "Testing outetts..."
+	bash test.sh
+	@echo "outetts tested."
+
+.PHONY: protogen-clean
+protogen-clean:
+	$(RM) backend_pb2_grpc.py backend_pb2.py
+
+.PHONY: clean
+clean: protogen-clean
+	rm -rf venv __pycache__

backend/python/outetts/backend.py

@@ -0,0 +1,138 @@
+#!/usr/bin/env python3
+"""
+gRPC server for OuteTTS (OuteAI TTS) models.
+"""
+from concurrent import futures
+
+import argparse
+import signal
+import sys
+import os
+import asyncio
+
+import backend_pb2
+import backend_pb2_grpc
+
+import grpc
+import outetts
+
+_ONE_DAY_IN_SECONDS = 60 * 60 * 24
+
+MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
+
+
+class BackendServicer(backend_pb2_grpc.BackendServicer):
+    def Health(self, request, context):
+        return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
+
+    def LoadModel(self, request, context):
+        model_name = request.Model
+        if os.path.exists(request.ModelFile):
+            model_name = request.ModelFile
+
+        self.options = {}
+        for opt in request.Options:
+            if ":" not in opt:
+                continue
+            key, value = opt.split(":", 1)
+            try:
+                if "." in value:
+                    value = float(value)
+                else:
+                    value = int(value)
+            except ValueError:
+                pass
+            self.options[key] = value
+
+        MODELNAME = "OuteAI/OuteTTS-0.3-1B"
+        TOKENIZER = "OuteAI/OuteTTS-0.3-1B"
+        VERSION = "0.3"
+        SPEAKER = "en_male_1"
+        for opt in request.Options:
+            if opt.startswith("tokenizer:"):
+                TOKENIZER = opt.split(":")[1]
+                break
+            if opt.startswith("version:"):
+                VERSION = opt.split(":")[1]
+                break
+            if opt.startswith("speaker:"):
+                SPEAKER = opt.split(":")[1]
+                break
+
+        if model_name != "":
+            MODELNAME = model_name
+
+        try:
+            model_config = outetts.HFModelConfig_v2(
+                model_path=MODELNAME,
+                tokenizer_path=TOKENIZER
+            )
+            self.interface = outetts.InterfaceHF(model_version=VERSION, cfg=model_config)
+
+            self.interface.print_default_speakers()
+            if request.AudioPath:
+                if os.path.isabs(request.AudioPath):
+                    self.AudioPath = request.AudioPath
+                else:
+                    self.AudioPath = os.path.join(request.ModelPath, request.AudioPath)
+                self.speaker = self.interface.create_speaker(audio_path=self.AudioPath)
+            else:
+                self.speaker = self.interface.load_default_speaker(name=SPEAKER)
+
+            if request.ContextSize > 0:
+                self.max_tokens = request.ContextSize
+            else:
+                self.max_tokens = self.options.get("max_new_tokens", 512)
+
+        except Exception as err:
+            print("Error:", err, file=sys.stderr)
+            return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
+        return backend_pb2.Result(message="Model loaded successfully", success=True)
+
+    def TTS(self, request, context):
+        try:
+            text = request.text if request.text else "Speech synthesis is the artificial production of human speech."
+            print("[OuteTTS] generating TTS", file=sys.stderr)
+            gen_cfg = outetts.GenerationConfig(
+                text=text,
+                temperature=self.options.get("temperature", 0.1),
+                repetition_penalty=self.options.get("repetition_penalty", 1.1),
+                max_length=self.max_tokens,
+                speaker=self.speaker,
+            )
+            output = self.interface.generate(config=gen_cfg)
+            print("[OuteTTS] Generated TTS", file=sys.stderr)
+            output.save(request.dst)
+            print("[OuteTTS] TTS done", file=sys.stderr)
+        except Exception as err:
+            return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
+        return backend_pb2.Result(success=True)
+
+
+async def serve(address):
+    server = grpc.aio.server(
+        migration_thread_pool=futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
+        options=[
+            ('grpc.max_message_length', 50 * 1024 * 1024),
+            ('grpc.max_send_message_length', 50 * 1024 * 1024),
+            ('grpc.max_receive_message_length', 50 * 1024 * 1024),
+        ])
+    backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
+    server.add_insecure_port(address)
+
+    loop = asyncio.get_event_loop()
+    for sig in (signal.SIGINT, signal.SIGTERM):
+        loop.add_signal_handler(
+            sig, lambda: asyncio.ensure_future(server.stop(5))
+        )
+
+    await server.start()
+    print("Server started. Listening on: " + address, file=sys.stderr)
+    await server.wait_for_termination()
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Run the OuteTTS gRPC server.")
+    parser.add_argument("--addr", default="localhost:50051", help="The address to bind the server to.")
+    args = parser.parse_args()
+    asyncio.run(serve(args.addr))

backend/python/outetts/install.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+set -e
+
+backend_dir=$(dirname $0)
+if [ -d $backend_dir/common ]; then
+    source $backend_dir/common/libbackend.sh
+else
+    source $backend_dir/../common/libbackend.sh
+fi
+
+installRequirements

backend/python/outetts/requirements-cpu.txt

@@ -0,0 +1,7 @@
+torch==2.7.1
+llvmlite==0.43.0
+numba==0.60.0
+accelerate
+bitsandbytes
+outetts
+protobuf==6.33.5

backend/python/outetts/requirements-cublas12.txt

@@ -0,0 +1,7 @@
+torch==2.7.1
+accelerate
+llvmlite==0.43.0
+numba==0.60.0
+bitsandbytes
+protobuf==6.33.5
+outetts

backend/python/outetts/requirements-cublas13.txt

@@ -0,0 +1,7 @@
+--extra-index-url https://download.pytorch.org/whl/cu130
+torch==2.9.0
+llvmlite==0.43.0
+numba==0.60.0
+bitsandbytes
+outetts
+protobuf==6.33.5

backend/python/outetts/requirements-hipblas.txt

@@ -0,0 +1,8 @@
+--extra-index-url https://download.pytorch.org/whl/rocm6.4
+torch==2.8.0+rocm6.4
+accelerate
+llvmlite==0.43.0
+numba==0.60.0
+bitsandbytes
+outetts
+protobuf==6.33.5

backend/python/outetts/requirements-intel.txt

@@ -0,0 +1,8 @@
+--extra-index-url https://download.pytorch.org/whl/xpu
+torch
+optimum[openvino]
+llvmlite==0.43.0
+numba==0.60.0
+bitsandbytes
+outetts
+protobuf==6.33.5

backend/python/outetts/requirements.txt

@@ -0,0 +1,6 @@
+grpcio==1.76.0
+protobuf==6.33.5
+certifi
+setuptools
+scipy==1.15.1
+numpy>=2.0.0

backend/python/outetts/run.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+backend_dir=$(dirname $0)
+if [ -d $backend_dir/common ]; then
+    source $backend_dir/common/libbackend.sh
+else
+    source $backend_dir/../common/libbackend.sh
+fi
+
+startBackend $@

backend/python/outetts/test.py

@@ -0,0 +1,35 @@
+"""
+Test script for the OuteTTS gRPC service.
+"""
+import unittest
+import subprocess
+import time
+import backend_pb2
+import backend_pb2_grpc
+
+import grpc
+
+
+class TestBackendServicer(unittest.TestCase):
+    def setUp(self):
+        self.service = subprocess.Popen(["python3", "backend.py", "--addr", "localhost:50051"])
+        time.sleep(5)
+
+    def tearDown(self):
+        self.service.terminate()
+        self.service.wait()
+
+    def test_health(self):
+        try:
+            with grpc.insecure_channel("localhost:50051") as channel:
+                stub = backend_pb2_grpc.BackendStub(channel)
+                response = stub.Health(backend_pb2.HealthMessage())
+                self.assertEqual(response.message, b'OK')
+        except Exception as err:
+            self.fail(f"Health check failed: {err}")
+        finally:
+            self.tearDown()
+
+
+if __name__ == "__main__":
+    unittest.main()

backend/python/outetts/test.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+set -e
+
+backend_dir=$(dirname $0)
+if [ -d $backend_dir/common ]; then
+    source $backend_dir/common/libbackend.sh
+else
+    source $backend_dir/../common/libbackend.sh
+fi
+
+runUnittests

backend/python/qwen-tts/requirements-mps.txt

@@ -1,4 +1,4 @@
-torch==2.7.1
-torchaudio==0.22.1
+torch
+torchaudio
 qwen-tts
-sox
+sox

backend/python/qwen-tts/test.py

@@ -28,7 +28,7 @@ class TestBackendServicer(unittest.TestCase):
             stderr=subprocess.PIPE,
             text=True
         )
-        time.sleep(5)
+        time.sleep(30)
 
     def tearDown(self) -> None:
         """

backend/python/rerankers/requirements-mps.txt

@@ -0,0 +1,4 @@
+torch==2.7.1
+transformers
+accelerate
+rerankers[transformers]

backend/python/rfdetr/requirements-mps.txt

@@ -0,0 +1,7 @@
+torch==2.7.1
+rfdetr
+opencv-python
+accelerate
+peft
+inference
+optimum-quanto

backend/python/transformers/backend.py

@@ -24,7 +24,6 @@ XPU=os.environ.get("XPU", "0") == "1"
 from transformers import AutoTokenizer, AutoModel, set_seed, TextIteratorStreamer, StoppingCriteriaList, StopStringCriteria, MambaConfig, MambaForCausalLM
 from transformers import AutoProcessor, MusicgenForConditionalGeneration, DiaForConditionalGeneration
 from scipy.io import wavfile
-import outetts
 from sentence_transformers import SentenceTransformer
 
 
@@ -89,7 +88,6 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
 
         self.CUDA = torch.cuda.is_available()
         self.OV=False
-        self.OuteTTS=False
         self.DiaTTS=False
         self.SentenceTransformer = False
 
@@ -239,45 +237,6 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                     self.processor = self.processor.to("cuda")
                 print("DiaForConditionalGeneration loaded", file=sys.stderr)
                 self.DiaTTS = True
-            elif request.Type == "OuteTTS":
-                autoTokenizer = False
-                options = request.Options
-                MODELNAME = "OuteAI/OuteTTS-0.3-1B"
-                TOKENIZER = "OuteAI/OuteTTS-0.3-1B"
-                VERSION = "0.3"
-                SPEAKER = "en_male_1"
-                for opt in options:
-                    if opt.startswith("tokenizer:"):
-                        TOKENIZER = opt.split(":")[1]
-                        break
-                    if opt.startswith("version:"):
-                        VERSION = opt.split(":")[1]
-                        break
-                    if opt.startswith("speaker:"):
-                        SPEAKER = opt.split(":")[1]
-                        break
-                
-                if model_name != "":
-                    MODELNAME = model_name
-
-                # Configure the model
-                model_config = outetts.HFModelConfig_v2(
-                    model_path=MODELNAME,
-                    tokenizer_path=TOKENIZER
-                )
-                # Initialize the interface
-                self.interface = outetts.InterfaceHF(model_version=VERSION, cfg=model_config)
-                self.OuteTTS = True
-
-                self.interface.print_default_speakers()
-                if request.AudioPath:
-                    if os.path.isabs(request.AudioPath):
-                        self.AudioPath = request.AudioPath
-                    else:
-                        self.AudioPath = os.path.join(request.ModelPath, request.AudioPath)
-                    self.speaker = self.interface.create_speaker(audio_path=self.AudioPath)
-                else:
-                    self.speaker = self.interface.load_default_speaker(name=SPEAKER)               
             elif request.Type == "SentenceTransformer":
                 autoTokenizer = False
                 self.model = SentenceTransformer(model_name, trust_remote_code=request.TrustRemoteCode)
@@ -588,30 +547,8 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         return backend_pb2.Result(success=True)
 
 
-    def CallOuteTTS(self, request, context):
-        try:
-            print("[OuteTTS] generating TTS", file=sys.stderr)
-            gen_cfg = outetts.GenerationConfig(
-                text="Speech synthesis is the artificial production of human speech.",
-                temperature=self.options.get("temperature", 0.1),
-                repetition_penalty=self.options.get("repetition_penalty", 1.1),
-                max_length=self.max_tokens,
-                speaker=self.speaker,
-                # voice_characteristics="upbeat enthusiasm, friendliness, clarity, professionalism, and trustworthiness"
-            )
-            output = self.interface.generate(config=gen_cfg)
-            print("[OuteTTS] Generated TTS", file=sys.stderr)
-            output.save(request.dst)
-            print("[OuteTTS] TTS done", file=sys.stderr)
-        except Exception as err:
-            return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
-        return backend_pb2.Result(success=True)
-
 # The TTS endpoint is older, and provides fewer features, but exists for compatibility reasons
     def TTS(self, request, context):
-        if self.OuteTTS:
-            return self.CallOuteTTS(request, context)
-        
         if self.DiaTTS:
             print("DiaTTS", file=sys.stderr)
             return self.CallDiaTTS(request, context)

backend/python/transformers/requirements-cpu.txt

@@ -4,6 +4,5 @@ numba==0.60.0
 accelerate
 transformers
 bitsandbytes
-outetts
-sentence-transformers==5.2.0
-protobuf==6.33.4
+sentence-transformers==5.2.2
+protobuf==6.33.5

backend/python/transformers/requirements-cublas12.txt

@@ -4,6 +4,5 @@ llvmlite==0.43.0
 numba==0.60.0
 transformers
 bitsandbytes
-outetts
-sentence-transformers==5.2.0
-protobuf==6.33.4
+sentence-transformers==5.2.2
+protobuf==6.33.5

backend/python/transformers/requirements-cublas13.txt

@@ -4,6 +4,5 @@ llvmlite==0.43.0
 numba==0.60.0
 transformers
 bitsandbytes
-outetts
-sentence-transformers==5.2.0
-protobuf==6.33.4
+sentence-transformers==5.2.2
+protobuf==6.33.5

backend/python/transformers/requirements-hipblas.txt

@@ -5,7 +5,5 @@ transformers
 llvmlite==0.43.0
 numba==0.60.0
 bitsandbytes
-outetts
-bitsandbytes
-sentence-transformers==5.2.0
-protobuf==6.33.4
+sentence-transformers==5.2.2
+protobuf==6.33.5

backend/python/transformers/requirements-intel.txt

@@ -5,6 +5,5 @@ llvmlite==0.43.0
 numba==0.60.0
 transformers
 bitsandbytes
-outetts
-sentence-transformers==5.2.0
-protobuf==6.33.4
+sentence-transformers==5.2.2
+protobuf==6.33.5

backend/python/transformers/requirements-mps.txt

@@ -0,0 +1,8 @@
+torch==2.7.1
+llvmlite==0.43.0
+numba==0.60.0
+accelerate
+transformers
+bitsandbytes
+sentence-transformers==5.2.2
+protobuf==6.33.5

backend/python/transformers/requirements.txt

@@ -1,5 +1,5 @@
 grpcio==1.76.0
-protobuf==6.33.4
+protobuf==6.33.5
 certifi
 setuptools
 scipy==1.15.1

backend/python/whisperx/install.sh

@@ -8,6 +8,8 @@ else
     source $backend_dir/../common/libbackend.sh
 fi
 
-EXTRA_PIP_INSTALL_FLAGS+=" --index-strategy unsafe-best-match"
+if [ "x${BUILD_PROFILE}" != "xmetal" ] && [ "x${BUILD_PROFILE}" != "xmps" ]; then
+    EXTRA_PIP_INSTALL_FLAGS+=" --index-strategy unsafe-best-match"
+fi
 
 installRequirements

backend/python/whisperx/requirements-mps.txt

@@ -0,0 +1,2 @@
+torch
+whisperx @ git+https://github.com/m-bain/whisperX.git

core/backend/soundgeneration.go

@@ -19,6 +19,14 @@ func SoundGeneration(
 	doSample *bool,
 	sourceFile *string,
 	sourceDivisor *int32,
+	think *bool,
+	caption string,
+	lyrics string,
+	bpm *int32,
+	keyscale string,
+	language string,
+	timesignature string,
+	instrumental *bool,
 	loader *model.ModelLoader,
 	appConfig *config.ApplicationConfig,
 	modelConfig config.ModelConfig,
@@ -45,8 +53,11 @@ func SoundGeneration(
 
 	fileName := utils.GenerateUniqueFileName(audioDir, "sound_generation", ".wav")
 	filePath := filepath.Join(audioDir, fileName)
+	if filePath, err = filepath.Abs(filePath); err != nil {
+		return "", nil, fmt.Errorf("failed resolving sound generation path: %w", err)
+	}
 
-	res, err := soundGenModel.SoundGeneration(context.Background(), &proto.SoundGenerationRequest{
+	req := &proto.SoundGenerationRequest{
 		Text:        text,
 		Model:       modelConfig.Model,
 		Dst:         filePath,
@@ -55,12 +66,38 @@ func SoundGeneration(
 		Temperature: temperature,
 		Src:         sourceFile,
 		SrcDivisor:  sourceDivisor,
-	})
-
-	// return RPC error if any
-	if !res.Success {
-		return "", nil, fmt.Errorf("error during sound generation: %s", res.Message)
+	}
+	if think != nil {
+		req.Think = think
+	}
+	if caption != "" {
+		req.Caption = &caption
+	}
+	if lyrics != "" {
+		req.Lyrics = &lyrics
+	}
+	if bpm != nil {
+		req.Bpm = bpm
+	}
+	if keyscale != "" {
+		req.Keyscale = &keyscale
+	}
+	if language != "" {
+		req.Language = &language
+	}
+	if timesignature != "" {
+		req.Timesignature = &timesignature
+	}
+	if instrumental != nil {
+		req.Instrumental = instrumental
 	}
 
-	return filePath, res, err
+	res, err := soundGenModel.SoundGeneration(context.Background(), req)
+	if err != nil {
+		return "", nil, err
+	}
+	if res != nil && !res.Success {
+		return "", nil, fmt.Errorf("error during sound generation: %s", res.Message)
+	}
+	return filePath, res, nil
 }

core/cli/soundgeneration.go

@@ -100,7 +100,9 @@ func (t *SoundGenerationCMD) Run(ctx *cliContext.Context) error {
 
 	filePath, _, err := backend.SoundGeneration(text,
 		parseToFloat32Ptr(t.Duration), parseToFloat32Ptr(t.Temperature), &t.DoSample,
-		inputFile, parseToInt32Ptr(t.InputFileSampleDivisor), ml, opts, options)
+		inputFile, parseToInt32Ptr(t.InputFileSampleDivisor),
+		nil, "", "", nil, "", "", "", nil,
+		ml, opts, options)
 
 	if err != nil {
 		return err

core/config/model_config.go

@@ -671,7 +671,8 @@ func (c *ModelConfig) GuessUsecases(u ModelConfigUsecase) bool {
 	}
 
 	if (u & FLAG_SOUND_GENERATION) == FLAG_SOUND_GENERATION {
-		if c.Backend != "transformers-musicgen" {
+		soundGenBackends := []string{"transformers-musicgen", "ace-step", "mock-backend"}
+		if !slices.Contains(soundGenBackends, c.Backend) {
 			return false
 		}
 	}

core/http/endpoints/elevenlabs/soundgeneration.go

@@ -32,8 +32,22 @@ func SoundGenerationEndpoint(cl *config.ModelConfigLoader, ml *model.ModelLoader
 
 		xlog.Debug("Sound Generation Request about to be sent to backend", "modelFile", "modelFile", "backend", cfg.Backend)
 
-		// TODO: Support uploading files?
-		filePath, _, err := backend.SoundGeneration(input.Text, input.Duration, input.Temperature, input.DoSample, nil, nil, ml, appConfig, *cfg)
+		language := input.Language
+		if language == "" {
+			language = input.VocalLanguage
+		}
+		var bpm *int32
+		if input.BPM != nil {
+			b := int32(*input.BPM)
+			bpm = &b
+		}
+		filePath, _, err := backend.SoundGeneration(
+			input.Text, input.Duration, input.Temperature, input.DoSample,
+			nil, nil,
+			input.Think, input.Caption, input.Lyrics, bpm, input.Keyscale,
+			language, input.Timesignature,
+			input.Instrumental,
+			ml, appConfig, *cfg)
 		if err != nil {
 			return err
 		}

core/http/endpoints/openai/realtime_model.go

@@ -28,7 +28,7 @@ type wrappedModel struct {
 	TTSConfig           *config.ModelConfig
 	TranscriptionConfig *config.ModelConfig
 	LLMConfig           *config.ModelConfig
-	VADConfig *config.ModelConfig
+	VADConfig           *config.ModelConfig
 
 	appConfig   *config.ApplicationConfig
 	modelLoader *model.ModelLoader
@@ -114,6 +114,35 @@ func (m *wrappedModel) Predict(ctx context.Context, messages schema.Messages, im
 					})
 				}
 			}
+
+			// Add noAction function before templating so it's included in the prompt
+			// Allow the user to set custom actions via config file
+			noActionName := "answer"
+			noActionDescription := "use this action to answer without performing any action"
+
+			if m.LLMConfig.FunctionsConfig.NoActionFunctionName != "" {
+				noActionName = m.LLMConfig.FunctionsConfig.NoActionFunctionName
+			}
+			if m.LLMConfig.FunctionsConfig.NoActionDescriptionName != "" {
+				noActionDescription = m.LLMConfig.FunctionsConfig.NoActionDescriptionName
+			}
+
+			noActionGrammar := functions.Function{
+				Name:        noActionName,
+				Description: noActionDescription,
+				Parameters: map[string]interface{}{
+					"properties": map[string]interface{}{
+						"message": map[string]interface{}{
+							"type":        "string",
+							"description": "The message to reply the user with",
+						},
+					},
+				},
+			}
+
+			if !m.LLMConfig.FunctionsConfig.DisableNoAction {
+				funcs = append(funcs, noActionGrammar)
+			}
 		}
 
 		predInput = m.evaluator.TemplateMessages(input, input.Messages, m.LLMConfig, funcs, len(funcs) > 0)
@@ -124,38 +153,29 @@ func (m *wrappedModel) Predict(ctx context.Context, messages schema.Messages, im
 		}
 	}
 
+	// Handle tool_choice parameter similar to the chat endpoint
+	if toolChoice != nil {
+		if toolChoice.Mode != "" {
+			// String values: "auto", "required", "none"
+			switch toolChoice.Mode {
+			case types.ToolChoiceModeRequired:
+				m.LLMConfig.SetFunctionCallString("required")
+			case types.ToolChoiceModeNone:
+				// Don't use tools
+				m.LLMConfig.SetFunctionCallString("none")
+			case types.ToolChoiceModeAuto:
+				// Default behavior - let model decide
+			}
+		} else if toolChoice.Function != nil {
+			// Specific function specified
+			m.LLMConfig.SetFunctionCallString(toolChoice.Function.Name)
+		}
+	}
+
 	// Generate grammar for function calling if tools are provided and grammar generation is enabled
 	shouldUseFn := len(tools) > 0 && m.LLMConfig.ShouldUseFunctions()
 
 	if !m.LLMConfig.FunctionsConfig.GrammarConfig.NoGrammar && shouldUseFn {
-		// Allow the user to set custom actions via config file
-		noActionName := "answer"
-		noActionDescription := "use this action to answer without performing any action"
-
-		if m.LLMConfig.FunctionsConfig.NoActionFunctionName != "" {
-			noActionName = m.LLMConfig.FunctionsConfig.NoActionFunctionName
-		}
-		if m.LLMConfig.FunctionsConfig.NoActionDescriptionName != "" {
-			noActionDescription = m.LLMConfig.FunctionsConfig.NoActionDescriptionName
-		}
-
-		noActionGrammar := functions.Function{
-			Name:        noActionName,
-			Description: noActionDescription,
-			Parameters: map[string]interface{}{
-				"properties": map[string]interface{}{
-					"message": map[string]interface{}{
-						"type":        "string",
-						"description": "The message to reply the user with",
-					},
-				},
-			},
-		}
-
-		if !m.LLMConfig.FunctionsConfig.DisableNoAction {
-			funcs = append(funcs, noActionGrammar)
-		}
-
 		// Force picking one of the functions by the request
 		if m.LLMConfig.FunctionToCall() != "" {
 			funcs = functions.Functions(funcs).Select(m.LLMConfig.FunctionToCall())
@@ -184,7 +204,7 @@ func (m *wrappedModel) Predict(ctx context.Context, messages schema.Messages, im
 		toolChoiceJSON = string(b)
 	}
 
-	return backend.ModelInference(ctx, predInput, messages, images, videos, audios, m.modelLoader, m.LLMConfig, m.confLoader, m.appConfig, tokenCallback, toolsJSON, toolChoiceJSON, logprobs, topLogprobs, logitBias, )
+	return backend.ModelInference(ctx, predInput, messages, images, videos, audios, m.modelLoader, m.LLMConfig, m.confLoader, m.appConfig, tokenCallback, toolsJSON, toolChoiceJSON, logprobs, topLogprobs, logitBias)
 }
 
 func (m *wrappedModel) TTS(ctx context.Context, text, voice, language string) (string, *proto.Result, error) {
@@ -218,11 +238,11 @@ func newTranscriptionOnlyModel(pipeline *config.Pipeline, cl *config.ModelConfig
 
 	return &transcriptOnlyModel{
 		TranscriptionConfig: cfgSST,
-		VADConfig: cfgVAD,
+		VADConfig:           cfgVAD,
 
-		confLoader: cl,
+		confLoader:  cl,
 		modelLoader: ml,
-		appConfig: appConfig,
+		appConfig:   appConfig,
 	}, cfgSST, nil
 }
 
@@ -297,11 +317,11 @@ func newModel(pipeline *config.Pipeline, cl *config.ModelConfigLoader, ml *model
 		TTSConfig:           cfgTTS,
 		TranscriptionConfig: cfgSST,
 		LLMConfig:           cfgLLM,
-		VADConfig: cfgVAD,
+		VADConfig:           cfgVAD,
 
-		confLoader: cl,
+		confLoader:  cl,
 		modelLoader: ml,
-		appConfig: appConfig,
-		evaluator: evaluator,
+		appConfig:   appConfig,
+		evaluator:   evaluator,
 	}, nil
 }

core/http/routes/ui.go

@@ -318,6 +318,49 @@ func RegisterUIRoutes(app *echo.Echo,
 		return c.Render(200, "views/tts", summary)
 	})
 
+	app.GET("/sound/:model", func(c echo.Context) error {
+		modelConfigs := cl.GetAllModelsConfigs()
+		modelsWithoutConfig, _ := services.ListModels(cl, ml, config.NoFilterFn, services.LOOSE_ONLY)
+
+		summary := map[string]interface{}{
+			"Title":               "LocalAI - Generate sound with " + c.Param("model"),
+			"BaseURL":             middleware.BaseURL(c),
+			"ModelsConfig":        modelConfigs,
+			"ModelsWithoutConfig": modelsWithoutConfig,
+			"Model":               c.Param("model"),
+			"Version":             internal.PrintableVersion(),
+		}
+		return c.Render(200, "views/sound", summary)
+	})
+
+	app.GET("/sound", func(c echo.Context) error {
+		modelConfigs := cl.GetAllModelsConfigs()
+		modelsWithoutConfig, _ := services.ListModels(cl, ml, config.NoFilterFn, services.LOOSE_ONLY)
+
+		if len(modelConfigs)+len(modelsWithoutConfig) == 0 {
+			return c.Redirect(302, middleware.BaseURL(c))
+		}
+
+		modelThatCanBeUsed := ""
+		title := "LocalAI - Generate sound"
+		for _, b := range modelConfigs {
+			if b.HasUsecases(config.FLAG_SOUND_GENERATION) {
+				modelThatCanBeUsed = b.Name
+				title = "LocalAI - Generate sound with " + modelThatCanBeUsed
+				break
+			}
+		}
+		summary := map[string]interface{}{
+			"Title":               title,
+			"BaseURL":             middleware.BaseURL(c),
+			"ModelsConfig":        modelConfigs,
+			"ModelsWithoutConfig": modelsWithoutConfig,
+			"Model":               modelThatCanBeUsed,
+			"Version":             internal.PrintableVersion(),
+		}
+		return c.Render(200, "views/sound", summary)
+	})
+
 	app.GET("/video/:model", func(c echo.Context) error {
 		modelConfigs := cl.GetAllModelsConfigs()
 		modelsWithoutConfig, _ := services.ListModels(cl, ml, config.NoFilterFn, services.LOOSE_ONLY)

core/http/static/sound.js

@@ -0,0 +1,144 @@
+function showNotification(type, message) {
+  const existing = document.getElementById('sound-notification');
+  if (existing) existing.remove();
+
+  const notification = document.createElement('div');
+  notification.id = 'sound-notification';
+  notification.className = 'fixed top-24 right-4 z-50 p-4 rounded-lg shadow-lg flex items-center gap-2 transition-all duration-300';
+  if (type === 'error') {
+    notification.classList.add('bg-red-900/90', 'border', 'border-red-700', 'text-red-200');
+    notification.innerHTML = '<i class="fas fa-circle-exclamation text-red-400 mr-2"></i>' + message;
+  } else {
+    notification.classList.add('bg-green-900/90', 'border', 'border-green-700', 'text-green-200');
+    notification.innerHTML = '<i class="fas fa-circle-check text-green-400 mr-2"></i>' + message;
+  }
+  document.body.appendChild(notification);
+  setTimeout(function() {
+    if (document.getElementById('sound-notification')) {
+      document.getElementById('sound-notification').remove();
+    }
+  }, 5000);
+}
+
+function buildRequestBody() {
+  const model = document.getElementById('sound-model').value;
+  const body = { model_id: model };
+  const isSimple = document.getElementById('mode-simple').checked;
+
+  if (isSimple) {
+    const text = document.getElementById('text').value.trim();
+    if (text) body.text = text;
+    body.instrumental = document.getElementById('instrumental').checked;
+    const vocal = document.getElementById('vocal_language').value.trim();
+    if (vocal) body.vocal_language = vocal;
+  } else {
+    // Advanced mode: do NOT send 'text' field - it triggers simple mode in backend
+    // Only send caption, lyrics, and other advanced fields
+    const caption = document.getElementById('caption').value.trim();
+    if (caption) body.caption = caption;
+    const lyrics = document.getElementById('lyrics').value.trim();
+    if (lyrics) body.lyrics = lyrics;
+    body.think = document.getElementById('think').checked;
+    const bpm = document.getElementById('bpm').value.trim();
+    if (bpm) body.bpm = parseInt(bpm, 10);
+    const duration = document.getElementById('duration_seconds').value.trim();
+    if (duration) body.duration_seconds = parseFloat(duration);
+    const keyscale = document.getElementById('keyscale').value.trim();
+    if (keyscale) body.keyscale = keyscale;
+    const language = document.getElementById('language').value.trim();
+    if (language) body.language = language;
+    const timesignature = document.getElementById('timesignature').value.trim();
+    if (timesignature) body.timesignature = timesignature;
+  }
+  return body;
+}
+
+async function generateSound(event) {
+  event.preventDefault();
+
+  const isSimple = document.getElementById('mode-simple').checked;
+  if (isSimple) {
+    const text = document.getElementById('text').value.trim();
+    if (!text) {
+      showNotification('error', 'Please enter text (description)');
+      return;
+    }
+  } else {
+    // Advanced mode: only check caption and lyrics (text field is hidden and not used)
+    const caption = document.getElementById('caption').value.trim();
+    const lyrics = document.getElementById('lyrics').value.trim();
+    if (!caption && !lyrics) {
+      showNotification('error', 'Please enter at least caption or lyrics');
+      return;
+    }
+  }
+
+  const loader = document.getElementById('loader');
+  const resultDiv = document.getElementById('result');
+  const generateBtn = document.getElementById('generate-btn');
+
+  loader.style.display = 'block';
+  generateBtn.disabled = true;
+  resultDiv.innerHTML = '<p class="text-[var(--color-text-secondary)] italic">Generating sound...</p>';
+
+  try {
+    const response = await fetch('v1/sound-generation', {
+      method: 'POST',
+      headers: { 'Content-Type': 'application/json' },
+      body: JSON.stringify(buildRequestBody()),
+    });
+
+    if (!response.ok) {
+      let errMsg = 'Request failed';
+      const ct = response.headers.get('content-type');
+      if (ct && ct.indexOf('application/json') !== -1) {
+        const json = await response.json();
+        if (json && json.error && json.error.message) errMsg = json.error.message;
+      }
+      resultDiv.innerHTML = '<div class="text-red-400 flex items-center gap-2"><i class="fas fa-circle-exclamation"></i> ' + errMsg + '</div>';
+      showNotification('error', 'Failed to generate sound');
+      return;
+    }
+
+    const blob = await response.blob();
+    const audioUrl = window.URL.createObjectURL(blob);
+
+    const wrap = document.createElement('div');
+    wrap.className = 'flex flex-col items-center gap-4 w-full';
+
+    const audio = document.createElement('audio');
+    audio.controls = true;
+    audio.src = audioUrl;
+    audio.className = 'w-full max-w-md';
+
+    const actions = document.createElement('div');
+    actions.className = 'flex flex-wrap justify-center gap-3';
+
+    const downloadLink = document.createElement('a');
+    downloadLink.href = audioUrl;
+    downloadLink.download = 'sound-' + new Date().toISOString().slice(0, 10) + '.wav';
+    downloadLink.className = 'inline-flex items-center gap-2 px-4 py-2 rounded-lg bg-[var(--color-primary)] text-[var(--color-bg-primary)] hover:opacity-90 transition';
+    downloadLink.innerHTML = '<i class="fas fa-download"></i> Download';
+
+    actions.appendChild(downloadLink);
+    wrap.appendChild(audio);
+    wrap.appendChild(actions);
+    resultDiv.innerHTML = '';
+    resultDiv.appendChild(wrap);
+
+    audio.play().catch(function() {});
+    showNotification('success', 'Sound generated successfully');
+  } catch (err) {
+    console.error('Sound generation error:', err);
+    resultDiv.innerHTML = '<div class="text-red-400 flex items-center gap-2"><i class="fas fa-circle-exclamation"></i> Network error</div>';
+    showNotification('error', 'Network error');
+  } finally {
+    loader.style.display = 'none';
+    generateBtn.disabled = false;
+  }
+}
+
+document.addEventListener('DOMContentLoaded', function() {
+  document.getElementById('sound-form').addEventListener('submit', generateSound);
+  document.getElementById('loader').style.display = 'none';
+});

core/http/views/manage.html

@@ -324,6 +324,11 @@
                                         <i class="fas fa-microphone text-[8px] mr-1"></i>TTS
                                     </a>
                                     {{ end }}
+                                    {{ if eq . "FLAG_SOUND_GENERATION" }}
+                                    <a href="sound/{{$backendCfg.Name}}" class="inline-flex items-center px-1.5 py-0.5 rounded text-[10px] font-medium bg-[var(--color-primary)]/10 text-[var(--color-primary)] hover:bg-[var(--color-primary)]/20 transition-colors" title="Sound">
+                                        <i class="fas fa-waveform-lines text-[8px] mr-1"></i>Sound
+                                    </a>
+                                    {{ end }}
                                     {{ end }}
                                 </div>
                             </td>

core/http/views/partials/navbar.html

@@ -34,6 +34,9 @@
                 <a href="tts/" class="text-[var(--color-text-secondary)] hover:text-[var(--color-text-primary)] px-2 py-2 rounded-lg transition duration-300 ease-in-out hover:bg-[var(--color-bg-secondary)] flex items-center group text-sm">
                     <i class="fa-solid fa-music text-[var(--color-primary)] mr-1.5 text-sm group-hover:scale-110 transition-transform"></i>TTS
                 </a>
+                <a href="sound/" class="text-[var(--color-text-secondary)] hover:text-[var(--color-text-primary)] px-2 py-2 rounded-lg transition duration-300 ease-in-out hover:bg-[var(--color-bg-secondary)] flex items-center group text-sm">
+                    <i class="fas fa-volume-high text-[var(--color-primary)] mr-1.5 text-sm group-hover:scale-110 transition-transform"></i>Sound
+                </a>
                 <a href="talk/" class="text-[var(--color-text-secondary)] hover:text-[var(--color-text-primary)] px-2 py-2 rounded-lg transition duration-300 ease-in-out hover:bg-[var(--color-bg-secondary)] flex items-center group text-sm">
                     <i class="fa-solid fa-phone text-[var(--color-primary)] mr-1.5 text-sm group-hover:scale-110 transition-transform"></i>Talk
                 </a>
@@ -97,6 +100,9 @@
                 <a href="tts/" class="block text-[var(--color-text-secondary)] hover:text-[var(--color-text-primary)] hover:bg-[var(--color-bg-secondary)] px-3 py-2 rounded-lg transition duration-300 ease-in-out flex items-center text-sm">
                     <i class="fa-solid fa-music text-[var(--color-primary)] mr-3 w-5 text-center text-sm"></i>TTS
                 </a>
+                <a href="sound/" class="block text-[var(--color-text-secondary)] hover:text-[var(--color-text-primary)] hover:bg-[var(--color-bg-secondary)] px-3 py-2 rounded-lg transition duration-300 ease-in-out flex items-center text-sm">
+                    <i class="fas fa-volume-high text-[var(--color-primary)] mr-3 w-5 text-center text-sm"></i>Sound
+                </a>
                 <a href="talk/" class="block text-[var(--color-text-secondary)] hover:text-[var(--color-text-primary)] hover:bg-[var(--color-bg-secondary)] px-3 py-2 rounded-lg transition duration-300 ease-in-out flex items-center text-sm">
                     <i class="fa-solid fa-phone text-[var(--color-primary)] mr-3 w-5 text-center text-sm"></i>Talk
                 </a>

core/http/views/sound.html

@@ -0,0 +1,187 @@
+<!DOCTYPE html>
+<html lang="en">
+{{template "views/partials/head" .}}
+<script defer src="static/sound.js"></script>
+
+<body class="bg-[var(--color-bg-primary)] text-[var(--color-text-primary)]">
+<div class="flex flex-col min-h-screen">
+
+    {{template "views/partials/navbar" .}}
+    <div class="container mx-auto px-4 py-8 flex-grow">
+        <!-- Hero Section -->
+        <div class="hero-section">
+            <div class="hero-content">
+                <h1 class="hero-title">
+                    <i class="fas fa-music mr-2"></i>Sound Generation {{ if .Model }} with {{.Model}} {{ end }}
+                </h1>
+                <p class="hero-subtitle">Generate music and audio from descriptions or structured prompts</p>
+            </div>
+        </div>
+
+        <!-- Sound Generation Interface -->
+        <div class="max-w-3xl mx-auto">
+            <div class="card overflow-hidden">
+                <!-- Header with Model Selection -->
+                <div class="border-b border-[var(--color-border)] p-5">
+                    <div class="flex flex-col sm:flex-row items-center justify-between gap-4">
+                        <div class="flex items-center" x-data="{ link : '{{ if .Model }}sound/{{.Model}}{{ end }}' }">
+                            <label for="model-select" class="mr-3 text-[var(--color-text-secondary)] font-medium">
+                                <i class="fas fa-microphone-lines text-[var(--color-primary)] mr-2"></i>Model:
+                            </label>
+                            <select
+                                id="model-select"
+                                x-model="link"
+                                @change="window.location = link"
+                                class="input p-2.5"
+                            >
+                                <option value="" disabled class="text-[var(--color-text-secondary)]">Select a model</option>
+                                {{ $model:=.Model}}
+                                {{ range .ModelsConfig }}
+                                    {{ $cfg := . }}
+                                    {{ range .KnownUsecaseStrings }}
+                                        {{ if eq . "FLAG_SOUND_GENERATION" }}
+                                            <option value="sound/{{$cfg.Name}}" {{ if eq $cfg.Name $model }} selected {{end}} class="bg-[var(--color-bg-primary)] text-[var(--color-text-primary)]">{{$cfg.Name}}</option>
+                                        {{ end }}
+                                    {{ end }}
+                                {{ end }}
+                                {{ range .ModelsWithoutConfig }}
+                                    <option value="sound/{{.}}" {{ if eq . $model }} selected {{ end }} class="bg-[var(--color-bg-primary)] text-[var(--color-text-primary)]">{{.}}</option>
+                                {{end}}
+                            </select>
+                        </div>
+                    </div>
+                </div>
+
+                <!-- Form -->
+                <div class="p-6">
+                    <div class="bg-[var(--color-primary)]/10 border border-[var(--color-primary-border)]/20 rounded-lg p-4 mb-6">
+                        <div class="flex items-start">
+                            <i class="fas fa-info-circle text-[var(--color-primary)] mt-1 mr-3 flex-shrink-0"></i>
+                            <p class="text-[var(--color-text-secondary)]">
+                                Use <strong>Simple mode</strong> (text as description + vocal language) or switch to <strong>Advanced mode</strong> for caption, lyrics, BPM, key, and more.
+                            </p>
+                        </div>
+                    </div>
+
+                    <input id="sound-model" type="hidden" value="{{.Model}}">
+                    <form id="sound-form" class="space-y-4">
+                        <!-- Mode toggle -->
+                        <div class="flex items-center gap-4">
+                            <span class="text-sm font-medium text-[var(--color-text-secondary)]">Mode:</span>
+                            <label class="inline-flex items-center cursor-pointer">
+                                <input type="radio" name="mode" value="simple" id="mode-simple" class="mr-2" checked>
+                                <span class="text-sm">Simple</span>
+                            </label>
+                            <label class="inline-flex items-center cursor-pointer">
+                                <input type="radio" name="mode" value="advanced" id="mode-advanced" class="mr-2">
+                                <span class="text-sm">Advanced</span>
+                            </label>
+                        </div>
+
+                        <!-- Text: used as description in simple mode, style in advanced mode -->
+                        <div class="space-y-4">
+                            <div id="text-field-container">
+                                <label for="text" class="block text-sm font-medium text-[var(--color-text-secondary)] mb-1.5">
+                                    <i class="fas fa-align-left text-[var(--color-primary)] mr-1.5"></i>Text <span id="text-label-desc" class="text-[var(--color-text-secondary)]">(description in simple mode)</span>
+                                </label>
+                                <textarea
+                                    id="text"
+                                    name="text"
+                                    placeholder="e.g. A soft Bengali love song for a quiet evening"
+                                    rows="3"
+                                    class="input w-full p-3"
+                                ></textarea>
+                            </div>
+                        </div>
+
+                        <!-- Simple mode -->
+                        <div id="simple-fields" class="space-y-4">
+                            <div class="flex flex-wrap items-center gap-4">
+                                <label class="inline-flex items-center cursor-pointer">
+                                    <input type="checkbox" id="instrumental" name="instrumental" class="rounded mr-2">
+                                    <span class="text-sm text-[var(--color-text-secondary)]">Instrumental only</span>
+                                </label>
+                                <div class="flex-1 min-w-[140px]">
+                                    <label for="vocal_language" class="block text-sm font-medium text-[var(--color-text-secondary)] mb-1">Vocal language</label>
+                                    <input type="text" id="vocal_language" name="vocal_language" placeholder="e.g. bn, en" class="input w-full p-2">
+                                </div>
+                            </div>
+                        </div>
+
+                        <!-- Advanced mode -->
+                        <div id="advanced-fields" class="hidden space-y-4">
+                            <div>
+                                <label for="caption" class="block text-sm font-medium text-[var(--color-text-secondary)] mb-1.5">Caption</label>
+                                <textarea id="caption" name="caption" placeholder="e.g. A funky Japanese disco track" rows="2" class="input w-full p-3"></textarea>
+                            </div>
+                            <div>
+                                <label for="lyrics" class="block text-sm font-medium text-[var(--color-text-secondary)] mb-1.5">Lyrics</label>
+                                <textarea id="lyrics" name="lyrics" placeholder="[Verse 1]&#10;..." rows="4" class="input w-full p-3 font-mono text-sm"></textarea>
+                            </div>
+                            <div class="flex flex-wrap items-center gap-4">
+                                <label class="inline-flex items-center cursor-pointer">
+                                    <input type="checkbox" id="think" name="think" class="rounded mr-2">
+                                    <span class="text-sm text-[var(--color-text-secondary)]">Think (reasoning)</span>
+                                </label>
+                                <div>
+                                    <label for="bpm" class="block text-xs text-[var(--color-text-secondary)] mb-0.5">BPM</label>
+                                    <input type="number" id="bpm" name="bpm" min="1" max="300" placeholder="120" class="input p-2 w-24">
+                                </div>
+                                <div>
+                                    <label for="duration_seconds" class="block text-xs text-[var(--color-text-secondary)] mb-0.5">Duration (s)</label>
+                                    <input type="number" id="duration_seconds" name="duration_seconds" min="1" placeholder="225" class="input p-2 w-24">
+                                </div>
+                                <div>
+                                    <label for="keyscale" class="block text-xs text-[var(--color-text-secondary)] mb-0.5">Key</label>
+                                    <input type="text" id="keyscale" name="keyscale" placeholder="e.g. Ab major" class="input p-2 w-28">
+                                </div>
+                                <div>
+                                    <label for="language" class="block text-xs text-[var(--color-text-secondary)] mb-0.5">Language</label>
+                                    <input type="text" id="language" name="language" placeholder="e.g. ja" class="input p-2 w-20">
+                                </div>
+                                <div>
+                                    <label for="timesignature" class="block text-xs text-[var(--color-text-secondary)] mb-0.5">Time sig.</label>
+                                    <input type="text" id="timesignature" name="timesignature" placeholder="4" class="input p-2 w-16">
+                                </div>
+                            </div>
+                        </div>
+
+                        <div class="pt-4">
+                            <button type="submit" id="generate-btn" class="btn-primary w-full py-3 flex items-center justify-center gap-2">
+                                <i class="fas fa-music"></i>
+                                <span>Generate sound</span>
+                            </button>
+                        </div>
+                    </form>
+
+                    <!-- Loading indicator -->
+                    <div class="flex justify-center my-6">
+                        <div id="loader" class="animate-spin rounded-full h-10 w-10 border-t-2 border-b-2 border-[var(--color-primary)]" style="display: none;"></div>
+                    </div>
+
+                    <!-- Results Area -->
+                    <div class="bg-[var(--color-bg-secondary)]/50 border border-[var(--color-border)] rounded-lg p-4 min-h-[100px] flex items-center justify-center">
+                        <div id="result" class="w-full"></div>
+                    </div>
+                </div>
+            </div>
+        </div>
+    </div>
+
+    {{template "views/partials/footer" .}}
+</div>
+
+<script>
+    document.getElementById('mode-simple').addEventListener('change', function() {
+        document.getElementById('simple-fields').classList.remove('hidden');
+        document.getElementById('advanced-fields').classList.add('hidden');
+        document.getElementById('text-field-container').classList.remove('hidden');
+    });
+    document.getElementById('mode-advanced').addEventListener('change', function() {
+        document.getElementById('simple-fields').classList.add('hidden');
+        document.getElementById('advanced-fields').classList.remove('hidden');
+        document.getElementById('text-field-container').classList.add('hidden');
+    });
+</script>
+</body>
+</html>

core/schema/elevenlabs.go

@@ -12,6 +12,17 @@ type ElevenLabsSoundGenerationRequest struct {
 	Duration    *float32 `json:"duration_seconds,omitempty" yaml:"duration_seconds,omitempty"`
 	Temperature *float32 `json:"prompt_influence,omitempty" yaml:"prompt_influence,omitempty"`
 	DoSample    *bool    `json:"do_sample,omitempty" yaml:"do_sample,omitempty"`
+	// Advanced mode
+	Think        *bool  `json:"think,omitempty" yaml:"think,omitempty"`
+	Caption      string `json:"caption,omitempty" yaml:"caption,omitempty"`
+	Lyrics       string `json:"lyrics,omitempty" yaml:"lyrics,omitempty"`
+	BPM          *int   `json:"bpm,omitempty" yaml:"bpm,omitempty"`
+	Keyscale     string `json:"keyscale,omitempty" yaml:"keyscale,omitempty"`
+	Language     string `json:"language,omitempty" yaml:"language,omitempty"`
+	VocalLanguage string `json:"vocal_language,omitempty" yaml:"vocal_language,omitempty"`
+	Timesignature string `json:"timesignature,omitempty" yaml:"timesignature,omitempty"`
+	// Simple mode: use text as description; optional instrumental / vocal_language
+	Instrumental *bool `json:"instrumental,omitempty" yaml:"instrumental,omitempty"`
 }
 
 func (elttsr *ElevenLabsTTSRequest) ModelName(s *string) string {

docs/content/features/audio-to-text.md

@@ -7,9 +7,12 @@ url = "/features/audio-to-text/"
 
 Audio to text models are models that can generate text from an audio file.
 
-The transcription endpoint allows to convert audio files to text. The endpoint is based
-on [whisper.cpp](https://github.com/ggerganov/whisper.cpp), a C++ library for audio transcription. The endpoint input
-supports all the audio formats supported by `ffmpeg`.
+The transcription endpoint allows to convert audio files to text. The endpoint supports multiple backends:
+- **[whisper.cpp](https://github.com/ggerganov/whisper.cpp)**: A C++ library for audio transcription (default)
+- **moonshine**: Ultra-fast transcription engine optimized for low-end devices
+- **faster-whisper**: Fast Whisper implementation with CTranslate2
+
+The endpoint input supports all the audio formats supported by `ffmpeg`.
 
 ## Usage
 

docs/content/features/text-to-audio.md

@@ -126,6 +126,64 @@ curl --request POST \
 
 Future versions of LocalAI will expose additional control over audio generation beyond the text prompt.
 
+### ACE-Step
+
+[ACE-Step 1.5](https://github.com/ACE-Step/ACE-Step-1.5) is a music generation model that can create music from text descriptions, lyrics, or audio samples. It supports both simple text-to-music and advanced music generation with metadata like BPM, key scale, and time signature.
+
+#### Setup
+
+Install the `ace-step-turbo` model from the Model gallery or run `local-ai run models install ace-step-turbo`.
+
+#### Usage
+
+ACE-Step supports two modes: **Simple mode** (text description + vocal language) and **Advanced mode** (caption, lyrics, BPM, key, and more).
+
+**Simple mode:**
+```bash
+curl http://localhost:8080/v1/audio/speech -H "Content-Type: application/json" -d '{
+  "model": "ace-step-turbo",
+  "input": "A soft Bengali love song for a quiet evening",
+  "vocal_language": "bn"
+}' --output music.flac
+```
+
+**Advanced mode** (using the `/sound` endpoint):
+```bash
+curl http://localhost:8080/sound -H "Content-Type: application/json" -d '{
+  "model": "ace-step-turbo",
+  "caption": "A funky Japanese disco track",
+  "lyrics": "[Verse 1]\n...",
+  "bpm": 120,
+  "keyscale": "Ab major",
+  "language": "ja",
+  "duration_seconds": 225
+}' --output music.flac
+```
+
+#### Configuration
+
+You can configure ACE-Step models with various options:
+
+```yaml
+name: ace-step-turbo
+backend: ace-step
+parameters:
+  model: acestep-v15-turbo
+known_usecases:
+  - sound_generation
+  - tts
+options:
+  - "device:auto"
+  - "use_flash_attention:true"
+  - "init_lm:true"  # Enable LLM for enhanced generation
+  - "lm_model_path:acestep-5Hz-lm-0.6B"  # or acestep-5Hz-lm-4B
+  - "lm_backend:pt"  # or vllm
+  - "temperature:0.85"
+  - "top_p:0.9"
+  - "inference_steps:8"
+  - "guidance_scale:7.0"
+```
+
 ### VibeVoice
 
 [VibeVoice-Realtime](https://github.com/microsoft/VibeVoice) is a real-time text-to-speech model that generates natural-sounding speech with voice cloning capabilities.

docs/content/installation/docker.md

@@ -150,7 +150,7 @@ services:
     ports:
       - 8080:8080
     environment:
-      - DEBUG=true
+      - DEBUG=false
     volumes:
       - ./models:/models:cached
     # For NVIDIA GPUs, uncomment:

gallery/index.yaml

@@ -1,4 +1,69 @@
 ---
+- name: "ace-step-turbo"
+  license: mit
+  tags:
+    - music
+    - audio
+    - music-generation
+    - tts
+    - sound-generation
+    - ace-step
+    - ace-step-1.5
+    - ace-step-1.5-turbo
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/ACE-Step/Ace-Step1.5
+  description: |
+    ACE-Step 1.5 Turbo is a music generation model that can create music from text descriptions,
+    lyrics, or audio samples. Supports both simple text-to-music and advanced music generation
+    with metadata like BPM, key scale, and time signature.
+  overrides:
+    name: ace-step-turbo
+    backend: ace-step
+    parameters:
+      model: acestep-v15-turbo
+    known_usecases:
+      - sound_generation
+      - tts
+    options:
+      - "device:auto"
+      - "use_flash_attention:true"
+      - "offload_to_cpu:false"
+      - "offload_dit_to_cpu:false"
+      - "init_lm:true"
+      - "lm_model_path:acestep-5Hz-lm-0.6B" # or acestep-5Hz-lm-4B
+      - "lm_backend:pt"
+      - "temperature:0.85"
+      - "top_p:0.9"
+      - "lm_cfg_scale:2.0"
+      - "inference_steps:8"
+      - "guidance_scale:7.0"
+      - "batch_size:1"
+- name: "qwen3-coder-next-mxfp4_moe"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF
+  description: |
+    The model is a quantized version of **Qwen/Qwen3-Coder-Next** (base model) using the **MXFP4** quantization scheme. It is optimized for efficiency while retaining performance, suitable for deployment in applications requiring lightweight inference. The quantized version is tailored for specific tasks, with parameters like temperature=1.0 and top_p=0.95 recommended for generation.
+  overrides:
+    parameters:
+      model: llama-cpp/models/Qwen3-Coder-Next-MXFP4_MOE.gguf
+    name: Qwen3-Coder-Next-MXFP4_MOE-GGUF
+    backend: llama-cpp
+    template:
+      use_tokenizer_template: true
+    known_usecases:
+      - chat
+    function:
+      grammar:
+        disable: true
+    description: Imported from https://huggingface.co/noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF
+    options:
+      - use_jinja:true
+  files:
+    - filename: llama-cpp/models/Qwen3-Coder-Next-MXFP4_MOE.gguf
+      sha256: fa356439e87010163778b7eab5f2b07e0e5b7f2cd9aac78b069139f5ae069414
+      uri: https://huggingface.co/noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF/resolve/main/Qwen3-Coder-Next-MXFP4_MOE.gguf
 - name: "deepseek-ai.deepseek-v3.2"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
@@ -1842,7 +1907,7 @@
     - gpu
     - text-to-speech
   overrides:
-    backend: "transformers"
+    backend: "outetts"
     name: "outetts"
     description: "OuteTTS is a 1.6B parameter text to speech model created by OuteAI."
     parameters:

go.mod

@@ -9,7 +9,7 @@ require (
 	fyne.io/fyne/v2 v2.7.2
 	github.com/Masterminds/sprig/v3 v3.3.0
 	github.com/alecthomas/kong v1.13.0
-	github.com/anthropics/anthropic-sdk-go v1.19.0
+	github.com/anthropics/anthropic-sdk-go v1.20.0
 	github.com/charmbracelet/glamour v0.10.0
 	github.com/containerd/containerd v1.7.30
 	github.com/ebitengine/purego v0.9.1
@@ -37,8 +37,9 @@ require (
 	github.com/mudler/go-processmanager v0.1.0
 	github.com/mudler/memory v0.0.0-20251216220809-d1256471a6c2
 	github.com/mudler/xlog v0.0.5
-	github.com/onsi/ginkgo/v2 v2.27.5
-	github.com/onsi/gomega v1.39.0
+	github.com/onsi/ginkgo/v2 v2.28.0
+	github.com/onsi/gomega v1.39.1
+	github.com/openai/openai-go/v3 v3.17.0
 	github.com/otiai10/copy v1.14.1
 	github.com/otiai10/openaigo v1.7.0
 	github.com/phayes/freeport v0.0.0-20220201140144-74d24b5ae9f5
@@ -54,10 +55,10 @@ require (
 	github.com/swaggo/swag v1.16.6
 	github.com/testcontainers/testcontainers-go v0.40.0
 	github.com/tmc/langchaingo v0.1.14
-	go.opentelemetry.io/otel v1.39.0
-	go.opentelemetry.io/otel/exporters/prometheus v0.61.0
-	go.opentelemetry.io/otel/metric v1.39.0
-	go.opentelemetry.io/otel/sdk/metric v1.39.0
+	go.opentelemetry.io/otel v1.40.0
+	go.opentelemetry.io/otel/exporters/prometheus v0.62.0
+	go.opentelemetry.io/otel/metric v1.40.0
+	go.opentelemetry.io/otel/sdk/metric v1.40.0
 	google.golang.org/grpc v1.78.0
 	gopkg.in/yaml.v2 v2.4.0
 	gopkg.in/yaml.v3 v3.0.1
@@ -67,14 +68,13 @@ require (
 require (
 	github.com/ghodss/yaml v1.0.0 // indirect
 	github.com/labstack/gommon v0.4.2 // indirect
-	github.com/openai/openai-go/v3 v3.17.0 // indirect
 	github.com/swaggo/files/v2 v2.0.2 // indirect
 	github.com/tidwall/gjson v1.18.0 // indirect
 	github.com/tidwall/match v1.2.0 // indirect
 	github.com/tidwall/pretty v1.2.1 // indirect
 	github.com/tidwall/sjson v1.2.5 // indirect
 	github.com/valyala/fasttemplate v1.2.2 // indirect
-	google.golang.org/protobuf v1.36.10 // indirect
+	google.golang.org/protobuf v1.36.11 // indirect
 )
 
 require (
@@ -155,9 +155,9 @@ require (
 	go.yaml.in/yaml/v2 v2.4.3
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
 	golang.org/x/image v0.25.0 // indirect
-	golang.org/x/net v0.48.0 // indirect; indirect (for websocket)
-	golang.org/x/oauth2 v0.33.0 // indirect
-	golang.org/x/telemetry v0.0.0-20251111182119-bc8e575c7b54 // indirect
+	golang.org/x/net v0.49.0 // indirect; indirect (for websocket)
+	golang.org/x/oauth2 v0.34.0 // indirect
+	golang.org/x/telemetry v0.0.0-20260109210033-bd525da824e2 // indirect
 	golang.org/x/time v0.14.0 // indirect
 )
 
@@ -211,7 +211,7 @@ require (
 	github.com/google/btree v1.1.3 // indirect
 	github.com/google/go-cmp v0.7.0 // indirect
 	github.com/google/gopacket v1.1.19 // indirect
-	github.com/google/pprof v0.0.0-20250630185457-6e76a2b096b5 // indirect
+	github.com/google/pprof v0.0.0-20260115054156-294ebfa9ad83 // indirect
 	github.com/gorilla/css v1.0.1 // indirect
 	github.com/gorilla/websocket v1.5.3
 	github.com/hashicorp/golang-lru v1.0.2 // indirect
@@ -289,7 +289,7 @@ require (
 	github.com/polydawn/refmt v0.89.0 // indirect
 	github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55 // indirect
 	github.com/prometheus/client_model v0.6.2 // indirect
-	github.com/prometheus/common v0.67.4 // indirect
+	github.com/prometheus/common v0.67.5 // indirect
 	github.com/prometheus/procfs v0.19.2 // indirect
 	github.com/quic-go/qpack v0.5.1 // indirect
 	github.com/quic-go/quic-go v0.54.1 // indirect
@@ -315,20 +315,20 @@ require (
 	github.com/yuin/goldmark-emoji v1.0.5 // indirect
 	github.com/yusufpapurcu/wmi v1.2.4 // indirect
 	go.opencensus.io v0.24.0 // indirect
-	go.opentelemetry.io/otel/sdk v1.39.0 // indirect
-	go.opentelemetry.io/otel/trace v1.39.0 // indirect
+	go.opentelemetry.io/otel/sdk v1.40.0 // indirect
+	go.opentelemetry.io/otel/trace v1.40.0 // indirect
 	go.uber.org/dig v1.19.0 // indirect
 	go.uber.org/fx v1.24.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
 	go.uber.org/zap v1.27.0 // indirect
-	golang.org/x/crypto v0.46.0 // indirect
+	golang.org/x/crypto v0.47.0 // indirect
 	golang.org/x/exp v0.0.0-20250606033433-dcc06ee1d476 // indirect
-	golang.org/x/mod v0.30.0 // indirect
+	golang.org/x/mod v0.32.0 // indirect
 	golang.org/x/sync v0.19.0 // indirect
 	golang.org/x/sys v0.40.0 // indirect
-	golang.org/x/term v0.38.0 // indirect
-	golang.org/x/text v0.32.0 // indirect
-	golang.org/x/tools v0.39.0 // indirect
+	golang.org/x/term v0.39.0 // indirect
+	golang.org/x/text v0.33.0 // indirect
+	golang.org/x/tools v0.41.0 // indirect
 	golang.zx2c4.com/wintun v0.0.0-20230126152724-0fa3db229ce2 // indirect
 	golang.zx2c4.com/wireguard v0.0.0-20250521234502-f333402bd9cb // indirect
 	golang.zx2c4.com/wireguard/windows v0.5.3 // indirect

go.sum

@@ -44,8 +44,8 @@ github.com/andybalholm/brotli v1.0.1/go.mod h1:loMXtMfwqflxFJPmdbJO0a3KNoPuLBgiu
 github.com/andybalholm/brotli v1.2.0 h1:ukwgCxwYrmACq68yiUqwIWnGY0cTPox/M94sVwToPjQ=
 github.com/andybalholm/brotli v1.2.0/go.mod h1:rzTDkvFWvIrjDXZHkuS16NPggd91W3kUSvPlQ1pLaKY=
 github.com/anmitsu/go-shlex v0.0.0-20161002113705-648efa622239/go.mod h1:2FmKhYUyUczH0OGQWaF5ceTx0UBShxjsH6f8oGKYe2c=
-github.com/anthropics/anthropic-sdk-go v1.19.0 h1:mO6E+ffSzLRvR/YUH9KJC0uGw0uV8GjISIuzem//3KE=
-github.com/anthropics/anthropic-sdk-go v1.19.0/go.mod h1:WTz31rIUHUHqai2UslPpw5CwXrQP3geYBioRV4WOLvE=
+github.com/anthropics/anthropic-sdk-go v1.20.0 h1:KE6gQiAT1aBHMh3Dmp1WgqnyZZLJNo2oX3ka004oDLE=
+github.com/anthropics/anthropic-sdk-go v1.20.0/go.mod h1:WTz31rIUHUHqai2UslPpw5CwXrQP3geYBioRV4WOLvE=
 github.com/aymanbagabas/go-osc52/v2 v2.0.1 h1:HwpRHbFMcZLEVr42D4p7XBqjyuxQH5SMiErDT4WkJ2k=
 github.com/aymanbagabas/go-osc52/v2 v2.0.1/go.mod h1:uYgXzlJ7ZpABp8OJ+exZzJJhRNQ2ASbcXHWsFqH8hp8=
 github.com/aymanbagabas/go-udiff v0.2.0 h1:TK0fH4MteXUDspT88n8CKzvK0X9O2xu9yQjWpi6yML8=
@@ -277,8 +277,8 @@ github.com/google/jsonschema-go v0.3.0 h1:6AH2TxVNtk3IlvkkhjrtbUc4S8AvO0Xii0DxIy
 github.com/google/jsonschema-go v0.3.0/go.mod h1:r5quNTdLOYEz95Ru18zA0ydNbBuYoo9tgaYcxEYhJVE=
 github.com/google/martian v2.1.0+incompatible/go.mod h1:9I4somxYTbIHy5NJKHRl3wXiIaQGbYVAs8BPL6v8lEs=
 github.com/google/pprof v0.0.0-20181206194817-3ea8567a2e57/go.mod h1:zfwlbNMJ+OItoe0UupaVj+oy1omPYYDuagoSzA8v9mc=
-github.com/google/pprof v0.0.0-20250630185457-6e76a2b096b5 h1:xhMrHhTJ6zxu3gA4enFM9MLn9AY7613teCdFnlUVbSQ=
-github.com/google/pprof v0.0.0-20250630185457-6e76a2b096b5/go.mod h1:5hDyRhoBCxViHszMt12TnOpEI4VVi+U8Gm9iphldiMA=
+github.com/google/pprof v0.0.0-20260115054156-294ebfa9ad83 h1:z2ogiKUYzX5Is6zr/vP9vJGqPwcdqsWjOt+V8J7+bTc=
+github.com/google/pprof v0.0.0-20260115054156-294ebfa9ad83/go.mod h1:MxpfABSjhmINe3F1It9d+8exIHFvUqtLIRCdOGNXqiI=
 github.com/google/renameio v0.1.0/go.mod h1:KWCgfxg9yswjAJkECMjeO8J8rahYeXnNhOm40UhjYkI=
 github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
@@ -561,10 +561,10 @@ github.com/nxadm/tail v1.4.8 h1:nPr65rt6Y5JFSKQO7qToXr7pePgD6Gwiw05lkbyAQTE=
 github.com/nxadm/tail v1.4.8/go.mod h1:+ncqLTQzXmGhMZNUePPaPqPvBxHAIsmXswZKocGu+AU=
 github.com/onsi/ginkgo v1.16.5 h1:8xi0RTUf59SOSfEtZMvwTvXYMzG4gV23XVHOZiXNtnE=
 github.com/onsi/ginkgo v1.16.5/go.mod h1:+E8gABHa3K6zRBolWtd+ROzc/U5bkGt0FwiG042wbpU=
-github.com/onsi/ginkgo/v2 v2.27.5 h1:ZeVgZMx2PDMdJm/+w5fE/OyG6ILo1Y3e+QX4zSR0zTE=
-github.com/onsi/ginkgo/v2 v2.27.5/go.mod h1:ArE1D/XhNXBXCBkKOLkbsb2c81dQHCRcF5zwn/ykDRo=
-github.com/onsi/gomega v1.39.0 h1:y2ROC3hKFmQZJNFeGAMeHZKkjBL65mIZcvrLQBF9k6Q=
-github.com/onsi/gomega v1.39.0/go.mod h1:ZCU1pkQcXDO5Sl9/VVEGlDyp+zm0m1cmeG5TOzLgdh4=
+github.com/onsi/ginkgo/v2 v2.28.0 h1:Rrf+lVLmtlBIKv6KrIGJCjyY8N36vDVcutbGJkyqjJc=
+github.com/onsi/ginkgo/v2 v2.28.0/go.mod h1:ArE1D/XhNXBXCBkKOLkbsb2c81dQHCRcF5zwn/ykDRo=
+github.com/onsi/gomega v1.39.1 h1:1IJLAad4zjPn2PsnhH70V4DKRFlrCzGBNrNaru+Vf28=
+github.com/onsi/gomega v1.39.1/go.mod h1:hL6yVALoTOxeWudERyfppUcZXjMwIMLnuSfruD2lcfg=
 github.com/openai/openai-go/v3 v3.17.0 h1:CfTkmQoItolSyW+bHOUF190KuX5+1Zv6MC0Gb4wAwy8=
 github.com/openai/openai-go/v3 v3.17.0/go.mod h1:cdufnVK14cWcT9qA1rRtrXx4FTRsgbDPW7Ia7SS5cZo=
 github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U=
@@ -652,8 +652,8 @@ github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:
 github.com/prometheus/client_model v0.6.2 h1:oBsgwpGs7iVziMvrGhE53c/GrLUsZdHnqNwqPLxwZyk=
 github.com/prometheus/client_model v0.6.2/go.mod h1:y3m2F6Gdpfy6Ut/GBsUqTWZqCUvMVzSfMLjcu6wAwpE=
 github.com/prometheus/common v0.0.0-20180801064454-c7de2306084e/go.mod h1:daVV7qP5qjZbuso7PdcryaAu0sAZbrN9i7WWcTMWvro=
-github.com/prometheus/common v0.67.4 h1:yR3NqWO1/UyO1w2PhUvXlGQs/PtFmoveVO0KZ4+Lvsc=
-github.com/prometheus/common v0.67.4/go.mod h1:gP0fq6YjjNCLssJCQp0yk4M8W6ikLURwkdd/YKtTbyI=
+github.com/prometheus/common v0.67.5 h1:pIgK94WWlQt1WLwAC5j2ynLaBRDiinoAb86HZHTUGI4=
+github.com/prometheus/common v0.67.5/go.mod h1:SjE/0MzDEEAyrdr5Gqc6G+sXI67maCxzaT3A2+HqjUw=
 github.com/prometheus/otlptranslator v1.0.0 h1:s0LJW/iN9dkIH+EnhiD3BlkkP5QVIUVEoIwkU+A6qos=
 github.com/prometheus/otlptranslator v1.0.0/go.mod h1:vRYWnXvI6aWGpsdY/mOT/cbeVRBlPWtBNDb7kGR3uKM=
 github.com/prometheus/procfs v0.0.0-20180725123919-05ee40e3a273/go.mod h1:c3At6R/oaqEKCNdg8wHV1ftS6bRYblBhIjjI8uT2IGk=
@@ -769,7 +769,6 @@ github.com/testcontainers/testcontainers-go v0.40.0/go.mod h1:FSXV5KQtX2HAMlm7U3
 github.com/tidwall/gjson v1.14.2/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
 github.com/tidwall/gjson v1.18.0 h1:FIDeeyB800efLX89e5a8Y0BNH+LOngJyGrIWxG2FKQY=
 github.com/tidwall/gjson v1.18.0/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
-github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA=
 github.com/tidwall/match v1.1.1/go.mod h1:eRSPERbgtNPcGhD8UCthc6PmLEQXEWd3PRB5JTxsfmM=
 github.com/tidwall/match v1.2.0 h1:0pt8FlkOwjN2fPt4bIl4BoNxb98gGHN2ObFEDkrfZnM=
 github.com/tidwall/match v1.2.0/go.mod h1:eRSPERbgtNPcGhD8UCthc6PmLEQXEWd3PRB5JTxsfmM=
@@ -834,22 +833,22 @@ go.opentelemetry.io/auto/sdk v1.2.1 h1:jXsnJ4Lmnqd11kwkBV2LgLoFMZKizbCi5fNZ/ipaZ
 go.opentelemetry.io/auto/sdk v1.2.1/go.mod h1:KRTj+aOaElaLi+wW1kO/DZRXwkF4C5xPbEe3ZiIhN7Y=
 go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0 h1:F7Jx+6hwnZ41NSFTO5q4LYDtJRXBf2PD0rNBkeB/lus=
 go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0/go.mod h1:UHB22Z8QsdRDrnAtX4PntOl36ajSxcdUMt1sF7Y6E7Q=
-go.opentelemetry.io/otel v1.39.0 h1:8yPrr/S0ND9QEfTfdP9V+SiwT4E0G7Y5MO7p85nis48=
-go.opentelemetry.io/otel v1.39.0/go.mod h1:kLlFTywNWrFyEdH0oj2xK0bFYZtHRYUdv1NklR/tgc8=
+go.opentelemetry.io/otel v1.40.0 h1:oA5YeOcpRTXq6NN7frwmwFR0Cn3RhTVZvXsP4duvCms=
+go.opentelemetry.io/otel v1.40.0/go.mod h1:IMb+uXZUKkMXdPddhwAHm6UfOwJyh4ct1ybIlV14J0g=
 go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.38.0 h1:GqRJVj7UmLjCVyVJ3ZFLdPRmhDUp2zFmQe3RHIOsw24=
 go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.38.0/go.mod h1:ri3aaHSmCTVYu2AWv44YMauwAQc0aqI9gHKIcSbI1pU=
 go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp v1.33.0 h1:wpMfgF8E1rkrT1Z6meFh1NDtownE9Ii3n3X2GJYjsaU=
 go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp v1.33.0/go.mod h1:wAy0T/dUbs468uOlkT31xjvqQgEVXv58BRFWEgn5v/0=
-go.opentelemetry.io/otel/exporters/prometheus v0.61.0 h1:cCyZS4dr67d30uDyh8etKM2QyDsQ4zC9ds3bdbrVoD0=
-go.opentelemetry.io/otel/exporters/prometheus v0.61.0/go.mod h1:iivMuj3xpR2DkUrUya3TPS/Z9h3dz7h01GxU+fQBRNg=
-go.opentelemetry.io/otel/metric v1.39.0 h1:d1UzonvEZriVfpNKEVmHXbdf909uGTOQjA0HF0Ls5Q0=
-go.opentelemetry.io/otel/metric v1.39.0/go.mod h1:jrZSWL33sD7bBxg1xjrqyDjnuzTUB0x1nBERXd7Ftcs=
-go.opentelemetry.io/otel/sdk v1.39.0 h1:nMLYcjVsvdui1B/4FRkwjzoRVsMK8uL/cj0OyhKzt18=
-go.opentelemetry.io/otel/sdk v1.39.0/go.mod h1:vDojkC4/jsTJsE+kh+LXYQlbL8CgrEcwmt1ENZszdJE=
-go.opentelemetry.io/otel/sdk/metric v1.39.0 h1:cXMVVFVgsIf2YL6QkRF4Urbr/aMInf+2WKg+sEJTtB8=
-go.opentelemetry.io/otel/sdk/metric v1.39.0/go.mod h1:xq9HEVH7qeX69/JnwEfp6fVq5wosJsY1mt4lLfYdVew=
-go.opentelemetry.io/otel/trace v1.39.0 h1:2d2vfpEDmCJ5zVYz7ijaJdOF59xLomrvj7bjt6/qCJI=
-go.opentelemetry.io/otel/trace v1.39.0/go.mod h1:88w4/PnZSazkGzz/w84VHpQafiU4EtqqlVdxWy+rNOA=
+go.opentelemetry.io/otel/exporters/prometheus v0.62.0 h1:krvC4JMfIOVdEuNPTtQ0ZjCiXrybhv+uOHMfHRmnvVo=
+go.opentelemetry.io/otel/exporters/prometheus v0.62.0/go.mod h1:fgOE6FM/swEnsVQCqCnbOfRV4tOnWPg7bVeo4izBuhQ=
+go.opentelemetry.io/otel/metric v1.40.0 h1:rcZe317KPftE2rstWIBitCdVp89A2HqjkxR3c11+p9g=
+go.opentelemetry.io/otel/metric v1.40.0/go.mod h1:ib/crwQH7N3r5kfiBZQbwrTge743UDc7DTFVZrrXnqc=
+go.opentelemetry.io/otel/sdk v1.40.0 h1:KHW/jUzgo6wsPh9At46+h4upjtccTmuZCFAc9OJ71f8=
+go.opentelemetry.io/otel/sdk v1.40.0/go.mod h1:Ph7EFdYvxq72Y8Li9q8KebuYUr2KoeyHx0DRMKrYBUE=
+go.opentelemetry.io/otel/sdk/metric v1.40.0 h1:mtmdVqgQkeRxHgRv4qhyJduP3fYJRMX4AtAlbuWdCYw=
+go.opentelemetry.io/otel/sdk/metric v1.40.0/go.mod h1:4Z2bGMf0KSK3uRjlczMOeMhKU2rhUqdWNoKcYrtcBPg=
+go.opentelemetry.io/otel/trace v1.40.0 h1:WA4etStDttCSYuhwvEa8OP8I5EWu24lkOzp+ZYblVjw=
+go.opentelemetry.io/otel/trace v1.40.0/go.mod h1:zeAhriXecNGP/s2SEG3+Y8X9ujcJOTqQ5RgdEJcawiA=
 go.opentelemetry.io/proto/otlp v1.8.0 h1:fRAZQDcAFHySxpJ1TwlA1cJ4tvcrw7nXl9xWWC8N5CE=
 go.opentelemetry.io/proto/otlp v1.8.0/go.mod h1:tIeYOeNBU4cvmPqpaji1P+KbB4Oloai8wN4rWzRrFF0=
 go.uber.org/atomic v1.6.0/go.mod h1:sABNBOSYdrvTF6hTgEIbc7YasKWGhgEQZyfxyTvoXHQ=
@@ -889,8 +888,8 @@ golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5y
 golang.org/x/crypto v0.8.0/go.mod h1:mRqEX+O9/h5TFCrQhkgjo2yKi0yYA+9ecGkdQoHrywE=
 golang.org/x/crypto v0.12.0/go.mod h1:NF0Gs7EO5K4qLn+Ylc+fih8BSTeIjAP05siRnAh98yw=
 golang.org/x/crypto v0.18.0/go.mod h1:R0j02AL6hcrfOiy9T4ZYp/rcWeMxM3L6QYxlOuEG1mg=
-golang.org/x/crypto v0.46.0 h1:cKRW/pmt1pKAfetfu+RCEvjvZkA9RimPbh7bhFjGVBU=
-golang.org/x/crypto v0.46.0/go.mod h1:Evb/oLKmMraqjZ2iQTwDwvCtJkczlDuTmdJXoZVzqU0=
+golang.org/x/crypto v0.47.0 h1:V6e3FRj+n4dbpw86FJ8Fv7XVOql7TEwpHapKoMJ/GO8=
+golang.org/x/crypto v0.47.0/go.mod h1:ff3Y9VzzKbwSSEzWqJsJVBnWmRwRSHt/6Op5n9bQc4A=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20250606033433-dcc06ee1d476 h1:bsqhLWFR6G6xiQcb+JoGqdKdRU6WzPWmK8E0jxTjzo4=
 golang.org/x/exp v0.0.0-20250606033433-dcc06ee1d476/go.mod h1:3//PLf8L/X+8b4vuAfHzxeRUl04Adcb341+IGKfnqS8=
@@ -908,8 +907,8 @@ golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
 golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
-golang.org/x/mod v0.30.0 h1:fDEXFVZ/fmCKProc/yAXXUijritrDzahmwwefnjoPFk=
-golang.org/x/mod v0.30.0/go.mod h1:lAsf5O2EvJeSFMiBxXDki7sCgAxEUcZHXoXMKT4GJKc=
+golang.org/x/mod v0.32.0 h1:9F4d3PHLljb6x//jOyokMv3eX+YDeepZSEo3mFJy93c=
+golang.org/x/mod v0.32.0/go.mod h1:SgipZ/3h2Ci89DlEtEXWUk/HteuRin+HHhN+WbNhguU=
 golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180906233101-161cd47e91fd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
@@ -933,14 +932,14 @@ golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns=
 golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
 golang.org/x/net v0.14.0/go.mod h1:PpSgVXXLK0OxS0F31C1/tv6XNguvCrnXIDrFMspZIUI=
 golang.org/x/net v0.20.0/go.mod h1:z8BVo6PvndSri0LbOE3hAn0apkU+1YvI6E70E9jsnvY=
-golang.org/x/net v0.48.0 h1:zyQRTTrjc33Lhh0fBgT/H3oZq9WuvRR5gPC70xpDiQU=
-golang.org/x/net v0.48.0/go.mod h1:+ndRgGjkh8FGtu1w1FGbEC31if4VrNVMuKTgcAAnQRY=
+golang.org/x/net v0.49.0 h1:eeHFmOGUTtaaPSGNmjBKpbng9MulQsJURQUAfUwY++o=
+golang.org/x/net v0.49.0/go.mod h1:/ysNB2EvaqvesRkuLAyjI1ycPZlQHM3q01F02UY/MV8=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20181017192945-9dcd33a902f4/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20181203162652-d668ce993890/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
-golang.org/x/oauth2 v0.33.0 h1:4Q+qn+E5z8gPRJfmRy7C2gGG3T4jIprK6aSYgTXGRpo=
-golang.org/x/oauth2 v0.33.0/go.mod h1:lzm5WQJQwKZ3nwavOZ3IS5Aulzxi68dUSgRHujetwEA=
+golang.org/x/oauth2 v0.34.0 h1:hqK/t4AKgbqWkdkcAeI8XLmbK+4m4G5YeQRrmiotGlw=
+golang.org/x/oauth2 v0.34.0/go.mod h1:lzm5WQJQwKZ3nwavOZ3IS5Aulzxi68dUSgRHujetwEA=
 golang.org/x/perf v0.0.0-20180704124530-6e6d33e29852/go.mod h1:JLpeXjPJfIyPr5TlbXLkXWLhP8nz10XfvxElABhCtcw=
 golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
@@ -984,8 +983,8 @@ golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.16.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/sys v0.40.0 h1:DBZZqJ2Rkml6QMQsZywtnjnnGvHza6BTfYFWY9kjEWQ=
 golang.org/x/sys v0.40.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
-golang.org/x/telemetry v0.0.0-20251111182119-bc8e575c7b54 h1:E2/AqCUMZGgd73TQkxUMcMla25GB9i/5HOdLr+uH7Vo=
-golang.org/x/telemetry v0.0.0-20251111182119-bc8e575c7b54/go.mod h1:hKdjCMrbv9skySur+Nek8Hd0uJ0GuxJIoIX2payrIdQ=
+golang.org/x/telemetry v0.0.0-20260109210033-bd525da824e2 h1:O1cMQHRfwNpDfDJerqRoE2oD+AFlyid87D40L/OkkJo=
+golang.org/x/telemetry v0.0.0-20260109210033-bd525da824e2/go.mod h1:b7fPSJ0pKZ3ccUh8gnTONJxhn3c/PS6tyzQvyqw4iA8=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
@@ -993,8 +992,8 @@ golang.org/x/term v0.7.0/go.mod h1:P32HKFT3hSsZrRxla30E9HqToFYAQPCMs/zFMBUFqPY=
 golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
 golang.org/x/term v0.11.0/go.mod h1:zC9APTIj3jG3FdV/Ons+XE1riIZXG4aZ4GTHiPZJPIU=
 golang.org/x/term v0.16.0/go.mod h1:yn7UURbUtPyrVJPGPq404EukNFxcm/foM+bV/bfcDsY=
-golang.org/x/term v0.38.0 h1:PQ5pkm/rLO6HnxFR7N2lJHOZX6Kez5Y1gDSJla6jo7Q=
-golang.org/x/term v0.38.0/go.mod h1:bSEAKrOT1W+VSu9TSCMtoGEOUcKxOKgl3LE5QEF/xVg=
+golang.org/x/term v0.39.0 h1:RclSuaJf32jOqZz74CkPA9qFuVTX7vhLlpfj/IGWlqY=
+golang.org/x/term v0.39.0/go.mod h1:yxzUCTP/U+FzoxfdKmLaA0RV1WgE0VY7hXBwKtY/4ww=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.1-0.20180807135948-17ff2d5776d2/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
@@ -1004,8 +1003,8 @@ golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
 golang.org/x/text v0.12.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
 golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
-golang.org/x/text v0.32.0 h1:ZD01bjUt1FQ9WJ0ClOL5vxgxOI/sVCNgX1YtKwcY0mU=
-golang.org/x/text v0.32.0/go.mod h1:o/rUWzghvpD5TXrTIBuJU77MTaN0ljMWE47kxGJQ7jY=
+golang.org/x/text v0.33.0 h1:B3njUFyqtHDUI5jMn1YIr5B0IE2U0qck04r6d4KPAxE=
+golang.org/x/text v0.33.0/go.mod h1:LuMebE6+rBincTi9+xWTY8TztLzKHc/9C1uBCG27+q8=
 golang.org/x/time v0.0.0-20180412165947-fbb02b2291d2/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.14.0 h1:MRx4UaLrDotUKUdCIqzPC48t1Y9hANFKIRpNx+Te8PI=
@@ -1027,8 +1026,8 @@ golang.org/x/tools v0.0.0-20200619180055-7c47624df98f/go.mod h1:EkVYQZoAsY45+roY
 golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
 golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
-golang.org/x/tools v0.39.0 h1:ik4ho21kwuQln40uelmciQPp9SipgNDdrafrYA4TmQQ=
-golang.org/x/tools v0.39.0/go.mod h1:JnefbkDPyD8UU2kI5fuf8ZX4/yUeh9W877ZeBONxUqQ=
+golang.org/x/tools v0.41.0 h1:a9b8iMweWG+S0OBnlU36rzLp20z1Rp10w+IY2czHTQc=
+golang.org/x/tools v0.41.0/go.mod h1:XSY6eDqxVNiYgezAVqqCeihT4j1U2CCsqvH3WhQpnlg=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
@@ -1079,8 +1078,8 @@ google.golang.org/protobuf v1.22.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2
 google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
 google.golang.org/protobuf v1.23.1-0.20200526195155-81db48ad09cc/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
 google.golang.org/protobuf v1.25.0/go.mod h1:9JNX74DMeImyA3h4bdi1ymwjUzf21/xIlbajtzgsN7c=
-google.golang.org/protobuf v1.36.10 h1:AYd7cD/uASjIL6Q9LiTjz8JLcrh/88q5UObnmY3aOOE=
-google.golang.org/protobuf v1.36.10/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=
+google.golang.org/protobuf v1.36.11 h1:fV6ZwhNocDyBLK0dj+fg8ektcVegBBuEolpbTQyBNVE=
+google.golang.org/protobuf v1.36.11/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=

swagger/docs.go

@@ -2123,12 +2123,30 @@ const docTemplate = `{
         "schema.ElevenLabsSoundGenerationRequest": {
             "type": "object",
             "properties": {
+                "bpm": {
+                    "type": "integer"
+                },
+                "caption": {
+                    "type": "string"
+                },
                 "do_sample": {
                     "type": "boolean"
                 },
                 "duration_seconds": {
                     "type": "number"
                 },
+                "instrumental": {
+                    "type": "boolean"
+                },
+                "keyscale": {
+                    "type": "string"
+                },
+                "language": {
+                    "type": "string"
+                },
+                "lyrics": {
+                    "type": "string"
+                },
                 "model_id": {
                     "type": "string"
                 },
@@ -2137,6 +2155,15 @@ const docTemplate = `{
                 },
                 "text": {
                     "type": "string"
+                },
+                "think": {
+                    "type": "boolean"
+                },
+                "timesignature": {
+                    "type": "string"
+                },
+                "vocal_language": {
+                    "type": "string"
                 }
             }
         },

swagger/swagger.json

@@ -2116,12 +2116,30 @@
         "schema.ElevenLabsSoundGenerationRequest": {
             "type": "object",
             "properties": {
+                "bpm": {
+                    "type": "integer"
+                },
+                "caption": {
+                    "type": "string"
+                },
                 "do_sample": {
                     "type": "boolean"
                 },
                 "duration_seconds": {
                     "type": "number"
                 },
+                "instrumental": {
+                    "type": "boolean"
+                },
+                "keyscale": {
+                    "type": "string"
+                },
+                "language": {
+                    "type": "string"
+                },
+                "lyrics": {
+                    "type": "string"
+                },
                 "model_id": {
                     "type": "string"
                 },
@@ -2130,6 +2148,15 @@
                 },
                 "text": {
                     "type": "string"
+                },
+                "think": {
+                    "type": "boolean"
+                },
+                "timesignature": {
+                    "type": "string"
+                },
+                "vocal_language": {
+                    "type": "string"
                 }
             }
         },

swagger/swagger.yaml

@@ -403,16 +403,34 @@ definitions:
     type: object
   schema.ElevenLabsSoundGenerationRequest:
     properties:
+      bpm:
+        type: integer
+      caption:
+        type: string
       do_sample:
         type: boolean
       duration_seconds:
         type: number
+      instrumental:
+        type: boolean
+      keyscale:
+        type: string
+      language:
+        type: string
+      lyrics:
+        type: string
       model_id:
         type: string
       prompt_influence:
         type: number
       text:
         type: string
+      think:
+        type: boolean
+      timesignature:
+        type: string
+      vocal_language:
+        type: string
     type: object
   schema.FunctionCall:
     properties:

tests/e2e/e2e_suite_test.go

@@ -109,11 +109,14 @@ var _ = BeforeSuite(func() {
 	// Create application
 	appCtx, appCancel = context.WithCancel(context.Background())
 
-	// Create application instance
+	// Create application instance (GeneratedContentDir so sound-generation/TTS can write files the handler sends)
+	generatedDir := filepath.Join(tmpDir, "generated")
+	Expect(os.MkdirAll(generatedDir, 0750)).To(Succeed())
 	application, err := application.New(
 		config.WithContext(appCtx),
 		config.WithSystemState(systemState),
 		config.WithDebug(true),
+		config.WithGeneratedContentDir(generatedDir),
 	)
 	Expect(err).ToNot(HaveOccurred())
 

tests/e2e/mock-backend/main.go

@@ -2,12 +2,14 @@ package main
 
 import (
 	"context"
+	"encoding/binary"
 	"encoding/json"
 	"flag"
 	"fmt"
 	"log"
 	"net"
 	"os"
+	"path/filepath"
 
 	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
 	"github.com/mudler/xlog"
@@ -142,13 +144,64 @@ func (m *MockBackend) TTSStream(in *pb.TTSRequest, stream pb.Backend_TTSStreamSe
 }
 
 func (m *MockBackend) SoundGeneration(ctx context.Context, in *pb.SoundGenerationRequest) (*pb.Result, error) {
-	xlog.Debug("SoundGeneration called", "text", in.Text)
+	xlog.Debug("SoundGeneration called",
+		"text", in.Text,
+		"caption", in.GetCaption(),
+		"lyrics", in.GetLyrics(),
+		"think", in.GetThink(),
+		"bpm", in.GetBpm(),
+		"keyscale", in.GetKeyscale(),
+		"language", in.GetLanguage(),
+		"timesignature", in.GetTimesignature(),
+		"instrumental", in.GetInstrumental())
+	dst := in.GetDst()
+	if dst != "" {
+		if err := os.MkdirAll(filepath.Dir(dst), 0750); err != nil {
+			return &pb.Result{Message: err.Error(), Success: false}, nil
+		}
+		if err := writeMinimalWAV(dst); err != nil {
+			return &pb.Result{Message: err.Error(), Success: false}, nil
+		}
+	}
 	return &pb.Result{
 		Message: "Sound generated successfully (mocked)",
 		Success: true,
 	}, nil
 }
 
+// writeMinimalWAV writes a minimal valid WAV file (short silence) so the HTTP handler can send it.
+func writeMinimalWAV(path string) error {
+	const sampleRate = 16000
+	const numChannels = 1
+	const bitsPerSample = 16
+	const numSamples = 1600 // 0.1s
+	dataSize := numSamples * numChannels * (bitsPerSample / 8)
+	const headerLen = 44
+	f, err := os.Create(path)
+	if err != nil {
+		return err
+	}
+	defer f.Close()
+	// RIFF header
+	_, _ = f.Write([]byte("RIFF"))
+	_ = binary.Write(f, binary.LittleEndian, uint32(headerLen-8+dataSize))
+	_, _ = f.Write([]byte("WAVE"))
+	// fmt chunk
+	_, _ = f.Write([]byte("fmt "))
+	_ = binary.Write(f, binary.LittleEndian, uint32(16))
+	_ = binary.Write(f, binary.LittleEndian, uint16(1))
+	_ = binary.Write(f, binary.LittleEndian, uint16(numChannels))
+	_ = binary.Write(f, binary.LittleEndian, uint32(sampleRate))
+	_ = binary.Write(f, binary.LittleEndian, uint32(sampleRate*numChannels*(bitsPerSample/8)))
+	_ = binary.Write(f, binary.LittleEndian, uint16(numChannels*(bitsPerSample/8)))
+	_ = binary.Write(f, binary.LittleEndian, uint16(bitsPerSample))
+	// data chunk
+	_, _ = f.Write([]byte("data"))
+	_ = binary.Write(f, binary.LittleEndian, uint32(dataSize))
+	_, _ = f.Write(make([]byte, dataSize))
+	return nil
+}
+
 func (m *MockBackend) AudioTranscription(ctx context.Context, in *pb.TranscriptRequest) (*pb.TranscriptResult, error) {
 	xlog.Debug("AudioTranscription called")
 	return &pb.TranscriptResult{

tests/e2e/mock_backend_test.go

@@ -96,6 +96,34 @@ var _ = Describe("Mock Backend E2E Tests", Label("MockBackend"), func() {
 		})
 	})
 
+	Describe("Sound Generation API", func() {
+		It("should generate mocked sound (simple mode)", func() {
+			body := `{"model_id":"mock-model","text":"a soft Bengali love song for a quiet evening","instrumental":false,"vocal_language":"bn"}`
+			req, err := http.NewRequest("POST", apiURL+"/sound-generation", io.NopCloser(strings.NewReader(body)))
+			Expect(err).ToNot(HaveOccurred())
+			req.Header.Set("Content-Type", "application/json")
+
+			httpClient := &http.Client{Timeout: 30 * time.Second}
+			resp, err := httpClient.Do(req)
+			Expect(err).ToNot(HaveOccurred())
+			defer resp.Body.Close()
+			Expect(resp.StatusCode).To(BeNumerically("<", 500))
+		})
+
+		It("should generate mocked sound (advanced mode)", func() {
+			body := `{"model_id":"mock-model","text":"upbeat pop","caption":"A funky Japanese disco track","lyrics":"[Verse 1]\nTest lyrics","think":true,"bpm":120,"duration_seconds":225,"keyscale":"Ab major","language":"ja","timesignature":"4"}`
+			req, err := http.NewRequest("POST", apiURL+"/sound-generation", io.NopCloser(strings.NewReader(body)))
+			Expect(err).ToNot(HaveOccurred())
+			req.Header.Set("Content-Type", "application/json")
+
+			httpClient := &http.Client{Timeout: 30 * time.Second}
+			resp, err := httpClient.Do(req)
+			Expect(err).ToNot(HaveOccurred())
+			defer resp.Body.Close()
+			Expect(resp.StatusCode).To(BeNumerically("<", 500))
+		})
+	})
+
 	Describe("Image Generation API", func() {
 		It("should generate mocked image", func() {
 			req, err := http.NewRequest("POST", apiURL+"/images/generations", nil)