feat: add VoxCPM tts backend

.github/workflows/backend.yml

@@ -118,6 +118,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
+          - build-type: 'cublas'
+            cuda-major-version: "12"
+            cuda-minor-version: "9"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-12-voxcpm'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "voxcpm"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "9"
@@ -366,6 +379,19 @@ 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-voxcpm'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "voxcpm"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "13"
             cuda-minor-version: "0"
@@ -719,6 +745,19 @@ 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-voxcpm'
+            runs-on: 'arc-runner-set'
+            base-image: "rocm/dev-ubuntu-24.04:6.4.4"
+            skip-drivers: 'false'
+            backend: "voxcpm"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'hipblas'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -942,6 +981,19 @@ 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-voxcpm'
+            runs-on: 'arc-runner-set'
+            base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+            skip-drivers: 'false'
+            backend: "voxcpm"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'intel'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -1341,6 +1393,19 @@ 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-voxcpm'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "voxcpm"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: ''
             cuda-major-version: ""
             cuda-minor-version: ""

.github/workflows/test-extra.yml

@@ -304,22 +304,22 @@ jobs:
         run: |
           make --jobs=5 --output-sync=target -C backend/python/qwen-tts
           make --jobs=5 --output-sync=target -C backend/python/qwen-tts test
-  # tests-vibevoice:
-  #   runs-on: bigger-runner
-  #   steps:
-  #     - name: Clone
-  #       uses: actions/checkout@v6
-  #       with:
-  #         submodules: true
-  #     - name: Dependencies
-  #       run: |
-  #         sudo apt-get update
-  #         sudo apt-get install -y build-essential ffmpeg
-  #         sudo apt-get install -y ca-certificates cmake curl patch python3-pip wget
-  #         # Install UV
-  #         curl -LsSf https://astral.sh/uv/install.sh | sh
-  #         pip install --user --no-cache-dir --break-system-packages grpcio-tools==1.64.1
-  #     - name: Test vibevoice
-  #       run: |
-  #         make --jobs=5 --output-sync=target -C backend/python/vibevoice
-  #         make --jobs=5 --output-sync=target -C backend/python/vibevoice test
+  tests-voxcpm:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clone
+        uses: actions/checkout@v6
+        with:
+          submodules: true
+      - name: Dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install build-essential ffmpeg
+          sudo apt-get install -y ca-certificates cmake curl patch python3-pip
+          # Install UV
+          curl -LsSf https://astral.sh/uv/install.sh | sh
+          pip install --user --no-cache-dir grpcio-tools==1.64.1
+      - name: Test voxcpm
+        run: |
+          make --jobs=5 --output-sync=target -C backend/python/voxcpm
+          make --jobs=5 --output-sync=target -C backend/python/voxcpm test

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
+.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/voxcpm
 
 GOCMD=go
 GOTEST=$(GOCMD) test
@@ -319,6 +319,7 @@ prepare-test-extra: protogen-python
 	$(MAKE) -C backend/python/moonshine
 	$(MAKE) -C backend/python/pocket-tts
 	$(MAKE) -C backend/python/qwen-tts
+	$(MAKE) -C backend/python/voxcpm
 
 test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/transformers test
@@ -330,6 +331,7 @@ test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/moonshine test
 	$(MAKE) -C backend/python/pocket-tts test
 	$(MAKE) -C backend/python/qwen-tts test
+	$(MAKE) -C backend/python/voxcpm test
 
 DOCKER_IMAGE?=local-ai
 DOCKER_AIO_IMAGE?=local-ai-aio
@@ -462,6 +464,7 @@ BACKEND_VIBEVOICE = vibevoice|python|.|--progress=plain|true
 BACKEND_MOONSHINE = moonshine|python|.|false|true
 BACKEND_POCKET_TTS = pocket-tts|python|.|false|true
 BACKEND_QWEN_TTS = qwen-tts|python|.|false|true
+BACKEND_VOXCPM = voxcpm|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)
@@ -507,12 +510,13 @@ $(eval $(call generate-docker-build-target,$(BACKEND_VIBEVOICE)))
 $(eval $(call generate-docker-build-target,$(BACKEND_MOONSHINE)))
 $(eval $(call generate-docker-build-target,$(BACKEND_POCKET_TTS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_QWEN_TTS)))
+$(eval $(call generate-docker-build-target,$(BACKEND_VOXCPM)))
 
 # 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-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-voxcpm
 
 ########################################################
 ### END Backends

backend/index.yaml

@@ -103,7 +103,7 @@
   capabilities:
     nvidia: "cuda12-rfdetr"
     intel: "intel-rfdetr"
     #amd: "rocm-rfdetr"
     nvidia-l4t: "nvidia-l4t-arm64-rfdetr"
     default: "cpu-rfdetr"
     nvidia-cuda-13: "cuda13-rfdetr"
@@ -414,6 +414,25 @@
     nvidia-l4t-cuda-12: "nvidia-l4t-qwen-tts"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-qwen-tts"
   icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png
+- &voxcpm
+  urls:
+    - https://github.com/ModelBest/VoxCPM
+  description: |
+    VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech.
+  tags:
+    - text-to-speech
+    - TTS
+  license: mit
+  name: "voxcpm"
+  alias: "voxcpm"
+  capabilities:
+    nvidia: "cuda12-voxcpm"
+    intel: "intel-voxcpm"
+    amd: "rocm-voxcpm"
+    default: "cpu-voxcpm"
+    nvidia-cuda-13: "cuda13-voxcpm"
+    nvidia-cuda-12: "cuda12-voxcpm"
+  icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4
 - &pocket-tts
   urls:
     - https://github.com/kyutai-labs/pocket-tts
@@ -986,7 +1005,7 @@
   capabilities:
     nvidia: "cuda12-rfdetr-development"
     intel: "intel-rfdetr-development"
     #amd: "rocm-rfdetr-development"
     nvidia-l4t: "nvidia-l4t-arm64-rfdetr-development"
     default: "cpu-rfdetr-development"
     nvidia-cuda-13: "cuda13-rfdetr-development"
@@ -1652,6 +1671,66 @@
   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
+## voxcpm
+- !!merge <<: *voxcpm
+  name: "voxcpm-development"
+  capabilities:
+    nvidia: "cuda12-voxcpm-development"
+    intel: "intel-voxcpm-development"
+    amd: "rocm-voxcpm-development"
+    default: "cpu-voxcpm-development"
+    nvidia-cuda-13: "cuda13-voxcpm-development"
+    nvidia-cuda-12: "cuda12-voxcpm-development"
+- !!merge <<: *voxcpm
+  name: "cpu-voxcpm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-voxcpm"
+  mirrors:
+    - localai/localai-backends:latest-cpu-voxcpm
+- !!merge <<: *voxcpm
+  name: "cpu-voxcpm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-voxcpm"
+  mirrors:
+    - localai/localai-backends:master-cpu-voxcpm
+- !!merge <<: *voxcpm
+  name: "cuda12-voxcpm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-voxcpm"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-voxcpm
+- !!merge <<: *voxcpm
+  name: "cuda12-voxcpm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-voxcpm"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-voxcpm
+- !!merge <<: *voxcpm
+  name: "cuda13-voxcpm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-voxcpm"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-voxcpm
+- !!merge <<: *voxcpm
+  name: "cuda13-voxcpm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-voxcpm"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-voxcpm
+- !!merge <<: *voxcpm
+  name: "intel-voxcpm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-voxcpm"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-voxcpm
+- !!merge <<: *voxcpm
+  name: "intel-voxcpm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-voxcpm"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-voxcpm
+- !!merge <<: *voxcpm
+  name: "rocm-voxcpm"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-voxcpm"
+  mirrors:
+    - localai/localai-backends:latest-gpu-rocm-hipblas-voxcpm
+- !!merge <<: *voxcpm
+  name: "rocm-voxcpm-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-voxcpm"
+  mirrors:
+    - localai/localai-backends:master-gpu-rocm-hipblas-voxcpm
 ## pocket-tts
 - !!merge <<: *pocket-tts
   name: "pocket-tts-development"

backend/python/voxcpm/Makefile

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