diff --git a/.github/backend-matrix.yml b/.github/backend-matrix.yml
index 118cfa300..9ff53684b 100644
--- a/.github/backend-matrix.yml
+++ b/.github/backend-matrix.yml
@@ -3234,9 +3234,10 @@ include:
   # consumed. Same reason CUDA needs its toolkit in base-image rather than in a
   # builder image: this is the ds4 shape, not the llama-cpp one.
   #
-  # No ROCm entry: upstream has no HIP configuration. No CUDA arm64 or L4T
-  # entry: upstream documents and validates CUDA on x86 only. Darwin/Metal is in
-  # the includeDarwin matrix below, built by scripts/build/audio-cpp-darwin.sh.
+  # ROCm uses upstream's HIP backend and the project-wide ROCm 7.2.1 base. No
+  # CUDA arm64 or L4T entry: upstream documents and validates CUDA on x86 only.
+  # Darwin/Metal is in the includeDarwin matrix below, built by
+  # scripts/build/audio-cpp-darwin.sh.
   #
   # No vulkan entry either, though Dockerfile.audio-cpp and the backend Makefile
   # both handle BUILD_TYPE=vulkan for local builds. Every other vulkan backend
@@ -3304,6 +3305,19 @@ include:
     dockerfile: "./backend/Dockerfile.audio-cpp"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'hipblas'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-rocm-hipblas-audio-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "rocm/dev-ubuntu-24.04:7.2.1"
+    skip-drivers: 'false'
+    backend: "audio-cpp"
+    dockerfile: "./backend/Dockerfile.audio-cpp"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: ''
     cuda-major-version: ""
     cuda-minor-version: ""
diff --git a/backend/Dockerfile.audio-cpp b/backend/Dockerfile.audio-cpp
index 993e2e3b6..108535d14 100644
--- a/backend/Dockerfile.audio-cpp
+++ b/backend/Dockerfile.audio-cpp
@@ -6,13 +6,14 @@ ARG APT_PORTS_MIRROR=""
 # ASR, VAD, diarization, source separation and music generation, wrapped as a
 # LocalAI gRPC backend.
 #
-# BASE_IMAGE is ubuntu:24.04 for cpu and vulkan builds, or
-# nvidia/cuda:<ver>-devel-ubuntu24.04 for cublas builds; both ship apt and
-# Ubuntu Noble packages, and the CUDA base additionally provides
-# /usr/local/cuda. BUILD_TYPE selects the engine backend in the Makefile:
-# "" = portable CPU with all ggml CPU variants, "cublas" ->
-# -DENGINE_ENABLE_CUDA=ON, "vulkan" -> -DENGINE_ENABLE_VULKAN=ON. Darwin
-# (Metal) builds bypass this Dockerfile entirely.
+# BASE_IMAGE is ubuntu:24.04 for cpu and vulkan builds,
+# nvidia/cuda:<ver>-devel-ubuntu24.04 for cublas builds, or
+# rocm/dev-ubuntu-24.04:<ver> for hipblas builds. All ship apt and Ubuntu Noble
+# packages; the GPU bases also provide their toolkits. BUILD_TYPE selects the
+# engine backend in the Makefile: "" = portable CPU with all ggml CPU variants,
+# "cublas" -> -DENGINE_ENABLE_CUDA=ON, "hipblas" -> -DENGINE_ENABLE_HIP=ON,
+# and "vulkan" -> -DENGINE_ENABLE_VULKAN=ON. Darwin (Metal) builds bypass this
+# Dockerfile entirely.
 #
 # Upstream needs GCC 13 or newer, which ubuntu:24.04 and the CUDA 12/13
 # devel-ubuntu24.04 images all provide.
@@ -62,7 +63,7 @@ ENV BUILD_TYPE=${BUILD_TYPE} \
     APT_MIRROR=${APT_MIRROR} \
     APT_PORTS_MIRROR=${APT_PORTS_MIRROR} \
     DEBIAN_FRONTEND=noninteractive \
-    PATH=/usr/local/cuda/bin:${PATH}
+    PATH=/opt/rocm/bin:/usr/local/cuda/bin:${PATH}
 
 WORKDIR /build
 
@@ -73,7 +74,7 @@ WORKDIR /build
 # fallback of its own.
 #
 # BUILD_TYPE=vulkan additionally needs the loader headers and glslc; both are in
-# Noble. The CUDA toolkit for BUILD_TYPE=cublas comes from BASE_IMAGE.
+# Noble. The CUDA and ROCm toolkits come from their matching BASE_IMAGE.
 RUN --mount=type=bind,source=.docker/apt-mirror.sh,target=/usr/local/sbin/apt-mirror \
     sh /usr/local/sbin/apt-mirror && \
     apt-get update && \
diff --git a/backend/cpp/audio-cpp/Makefile b/backend/cpp/audio-cpp/Makefile
index 2c26ea926..cf7b29568 100644
--- a/backend/cpp/audio-cpp/Makefile
+++ b/backend/cpp/audio-cpp/Makefile
@@ -77,6 +77,13 @@ endif
 
 ifeq ($(BUILD_TYPE),cublas)
     CMAKE_ARGS += -DENGINE_ENABLE_CUDA=ON "-DCMAKE_CUDA_ARCHITECTURES=$(CUDA_ARCHITECTURES)"
+else ifeq ($(BUILD_TYPE),hipblas)
+    ROCM_HOME ?= /opt/rocm
+    ROCM_PATH ?= /opt/rocm
+    export CXX=$(ROCM_HOME)/llvm/bin/clang++
+    export CC=$(ROCM_HOME)/llvm/bin/clang
+    AMDGPU_TARGETS ?= gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201
+    CMAKE_ARGS += -DENGINE_ENABLE_HIP=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
 else ifeq ($(BUILD_TYPE),vulkan)
     CMAKE_ARGS += -DENGINE_ENABLE_VULKAN=ON
 else ifeq ($(UNAME_S),Darwin)
diff --git a/backend/cpp/audio-cpp/loaded_model.cpp b/backend/cpp/audio-cpp/loaded_model.cpp
index 77dc10442..28bed59b3 100644
--- a/backend/cpp/audio-cpp/loaded_model.cpp
+++ b/backend/cpp/audio-cpp/loaded_model.cpp
@@ -103,6 +103,9 @@ engine::core::BackendType parse_backend_type(const std::string &value) {
     if (value == "cuda") {
         return engine::core::BackendType::Cuda;
     }
+    if (value == "hip" || value == "rocm") {
+        return engine::core::BackendType::Hip;
+    }
     if (value == "vulkan") {
         return engine::core::BackendType::Vulkan;
     }
@@ -116,7 +119,7 @@ engine::core::BackendType parse_backend_type(const std::string &value) {
         return engine::core::BackendType::Cpu;
     }
     throw ConfigError("audio-cpp: unknown backend option '" + value +
-                      "'. Known backends: cpu, cuda, vulkan, metal, best");
+                      "'. Known backends: cpu, cuda, hip, rocm, vulkan, metal, best");
 }
 
 std::filesystem::path executable_directory() {
diff --git a/backend/cpp/audio-cpp/model_options.cpp b/backend/cpp/audio-cpp/model_options.cpp
index 7a4b8c277..7c5f8d8fd 100644
--- a/backend/cpp/audio-cpp/model_options.cpp
+++ b/backend/cpp/audio-cpp/model_options.cpp
@@ -59,6 +59,12 @@ bool starts_with(const std::string &value, const std::string &prefix) {
            value.compare(0, prefix.size(), prefix) == 0;
 }
 
+bool is_known_backend(const std::string &value) {
+    return value == "cpu" || value == "cuda" || value == "hip" ||
+           value == "rocm" || value == "vulkan" || value == "metal" ||
+           value == "best";
+}
+
 } // namespace
 
 ParsedOptions parse_model_options(const std::vector<std::string> &entries) {
@@ -107,6 +113,12 @@ ParsedOptions parse_model_options(const std::vector<std::string> &entries) {
         } else if (key == "task") {
             parsed.options.task = value;
         } else if (key == "backend") {
+            if (!is_known_backend(value)) {
+                parsed.error = "audio-cpp: unknown backend option '" + value +
+                               "'. Known backends: cpu, cuda, hip, rocm, "
+                               "vulkan, metal, best";
+                return parsed;
+            }
             parsed.options.backend = value;
         } else if (key == "model_spec_override") {
             parsed.options.model_spec_override = value;
diff --git a/backend/cpp/audio-cpp/model_options.h b/backend/cpp/audio-cpp/model_options.h
index 9cb4464f8..0a5079e97 100644
--- a/backend/cpp/audio-cpp/model_options.h
+++ b/backend/cpp/audio-cpp/model_options.h
@@ -17,7 +17,7 @@ struct ModelOptions {
     std::string family;
     // Pins the audio.cpp task, overriding RPC-based routing. Empty means route.
     std::string task;
-    // ggml backend: cpu, cuda, vulkan, metal, best.
+    // ggml backend: cpu, cuda, hip (or rocm), vulkan, metal, best.
     std::string backend = "cpu";
     int device = 0;
     // True once a `device:` entry has been seen. 0 is both the default and a
diff --git a/backend/cpp/audio-cpp/model_options_test.cpp b/backend/cpp/audio-cpp/model_options_test.cpp
index c3cb2f75a..57abc567f 100644
--- a/backend/cpp/audio-cpp/model_options_test.cpp
+++ b/backend/cpp/audio-cpp/model_options_test.cpp
@@ -75,6 +75,11 @@ static void test_scalar_options() {
     check(parse_model_options({"live_idle_timeout_ms:0"}).options.live_idle_timeout_ms == 0,
           "an explicit 0 turns the live idle limit off rather than reverting to "
           "the default");
+
+    check(parse_model_options({"backend:hip"}).error.empty(),
+          "HIP backend option is accepted");
+    check(parse_model_options({"backend:rocm"}).error.empty(),
+          "ROCm backend alias is accepted");
 }
 
 // Values containing colons must survive: split on the FIRST colon only.
@@ -124,6 +129,8 @@ static void test_errors() {
           "negative device is rejected");
     check(!parse_model_options({"threads:x"}).error.empty(),
           "non-numeric threads is rejected");
+    check(!parse_model_options({"backend:unknown"}).error.empty(),
+          "unknown compute backend is rejected before model loading");
 
     // Values too large for int must be rejected, not silently wrapped into a
     // negative device index that then reaches the ggml backend selector.
diff --git a/backend/index.yaml b/backend/index.yaml
index dfd3dfb48..b3a79e587 100644
--- a/backend/index.yaml
+++ b/backend/index.yaml
@@ -150,6 +150,7 @@
     - audio-transcription
     - CPU
     - CUDA
+    - HIP
     - Metal
   # No vulkan key: the vulkan image would carry a Vulkan loader with no Mesa ICD
   # (see the audio-cpp block in .github/backend-matrix.yml). Pointing a
@@ -161,6 +162,7 @@
     nvidia: "cuda12-audio-cpp"
     nvidia-cuda-12: "cuda12-audio-cpp"
     nvidia-cuda-13: "cuda13-audio-cpp"
+    amd: "rocm-audio-cpp"
     metal: "metal-audio-cpp"
     metal-darwin-arm64: "metal-audio-cpp"
 - &whispercpp
@@ -2136,6 +2138,7 @@
     nvidia: "cuda12-audio-cpp-development"
     nvidia-cuda-12: "cuda12-audio-cpp-development"
     nvidia-cuda-13: "cuda13-audio-cpp-development"
+    amd: "rocm-audio-cpp-development"
     metal: "metal-audio-cpp-development"
     metal-darwin-arm64: "metal-audio-cpp-development"
 - !!merge <<: *stablediffusionggml
@@ -7131,6 +7134,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-audio-cpp"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-audio-cpp
+- !!merge <<: *audiocpp
+  name: "rocm-audio-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-audio-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-rocm-hipblas-audio-cpp
+- !!merge <<: *audiocpp
+  name: "rocm-audio-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-audio-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-rocm-hipblas-audio-cpp
 - !!merge <<: *audiocpp
   name: "metal-audio-cpp"
   uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-audio-cpp"
diff --git a/core/gallery/backends_test.go b/core/gallery/backends_test.go
index 1b7e059be..4424c165c 100644
--- a/core/gallery/backends_test.go
+++ b/core/gallery/backends_test.go
@@ -68,6 +68,49 @@ var _ = Describe("Runtime capability-based backend selection", func() {
 		Expect(cpuArchitectures).To(ConsistOf("linux/amd64/amd64", "linux/arm64/arm64"))
 	})
 
+	It("keeps the audio.cpp ROCm image connected to the AMD capability", func() {
+		backends, err := ReadConfigFile[[]*GalleryBackend](filepath.Join("..", "..", "backend", "index.yaml"))
+		Expect(err).NotTo(HaveOccurred())
+
+		byName := make(map[string]*GalleryBackend, len(*backends))
+		for _, backend := range *backends {
+			byName[backend.Name] = backend
+		}
+
+		Expect(byName).To(HaveKey("audio-cpp"))
+		Expect(byName["audio-cpp"].CapabilitiesMap).To(HaveKeyWithValue("amd", "rocm-audio-cpp"))
+		Expect(byName).To(HaveKey("rocm-audio-cpp"))
+		Expect(byName["rocm-audio-cpp"].URI).To(Equal("quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-audio-cpp"))
+
+		type matrixEntry struct {
+			Backend   string `yaml:"backend"`
+			BuildType string `yaml:"build-type"`
+			Platforms string `yaml:"platforms"`
+			TagSuffix string `yaml:"tag-suffix"`
+			BaseImage string `yaml:"base-image"`
+		}
+		type backendMatrix struct {
+			Include []matrixEntry `yaml:"include"`
+		}
+
+		matrix, err := ReadConfigFile[backendMatrix](filepath.Join("..", "..", ".github", "backend-matrix.yml"))
+		Expect(err).NotTo(HaveOccurred())
+
+		var rocmEntries []matrixEntry
+		for _, entry := range matrix.Include {
+			if entry.Backend == "audio-cpp" && entry.BuildType == "hipblas" {
+				rocmEntries = append(rocmEntries, entry)
+			}
+		}
+		Expect(rocmEntries).To(ConsistOf(matrixEntry{
+			Backend:   "audio-cpp",
+			BuildType: "hipblas",
+			Platforms: "linux/amd64",
+			TagSuffix: "-gpu-rocm-hipblas-audio-cpp",
+			BaseImage: "rocm/dev-ubuntu-24.04:7.2.1",
+		}))
+	})
+
 	It("ListSystemBackends prefers optimal alias candidate", func() {
 		// Arrange two installed backends sharing the same alias
 		must := func(err error) { Expect(err).NotTo(HaveOccurred()) }
diff --git a/docs/content/features/audio-cpp.md b/docs/content/features/audio-cpp.md
index 9d59cb378..f3a7ce4be 100644
--- a/docs/content/features/audio-cpp.md
+++ b/docs/content/features/audio-cpp.md
@@ -109,7 +109,7 @@ listing the keys that exist, rather than being silently ignored.
 |---|---|---|
 | `family:<name>` | read from the GGUF | The audio.cpp family. Optional for a standalone audio.cpp GGUF, which embeds `audiocpp.model_spec.family`. Required for a safetensors file or a package directory. Setting it explicitly also overrides the embedded value. |
 | `task:<name>` | routed from the RPC | Pins the task. One of `gen`, `tts`, `clon`, `vc`, `svc`, `s2s`, `asr`, `align`, `vad`, `diar`, `sep`, `vdes`, `spk`. A pinned task is honoured exactly: if the family cannot serve it, the request is refused rather than rerouted. |
-| `backend:<name>` | `cpu` | ggml compute backend: `cpu`, `cuda`, `vulkan`, `metal`, `best`. Must match the backend image you installed (a `cuda` value needs the CUDA image). |
+| `backend:<name>` | `cpu` | ggml compute backend: `cpu`, `cuda`, `hip` (`rocm` is an alias), `vulkan`, `metal`, `best`. Must match the backend image you installed (a `hip` value needs the ROCm image). |
 | `device:<n>` | `0` | GPU index for the selected compute backend. Non-negative integer. |
 | `threads:<n>` | runtime default | CPU threads. `0` leaves the choice to the runtime. |
 | `busy_timeout_ms:<n>` | `0` (unbounded) | Bounds the wait for the model's single inference lane. A request that arrives while a run has already been in flight longer than this fails immediately with `UNAVAILABLE` instead of queueing, and a request that waits this long without the lane freeing up fails the same way. `0` waits indefinitely. |
@@ -245,8 +245,11 @@ voice conversion from the same weights.
 | CPU | linux/amd64, linux/arm64 |
 | CUDA 12 | linux/amd64 |
 | CUDA 13 | linux/amd64 |
+| ROCm 7.2 | linux/amd64 |
 | Metal | darwin/arm64 |
 
-There is no ROCm image, because upstream has no HIP build configuration, and no Vulkan
-image: it would ship a Vulkan loader with no ICD inside the container. `BUILD_TYPE=vulkan`
-still works when building the backend yourself.
+The ROCm image includes kernels for these GPU targets:
+`gfx908`, `gfx90a`, `gfx942`, `gfx950`, `gfx1030`, `gfx1100`, `gfx1101`, `gfx1102`,
+`gfx1151`, `gfx1200` and `gfx1201`. Set the model option to `backend:hip` or
+`backend:rocm`. There is no Vulkan image because the container would have no Vulkan ICD.
+`BUILD_TYPE=vulkan` still works when you build the backend yourself.