feat(vibevoice): add new backend

.github/workflows/backend.yml

@@ -198,6 +198,19 @@ jobs:
             context: "./backend"
             ubuntu-version: '2204'
           # CUDA 12 builds
+          - build-type: 'cublas'
+            cuda-major-version: "12"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-12-vibevoice'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "vibevoice"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
+            ubuntu-version: '2204'
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -407,6 +420,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
             ubuntu-version: '2204'
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13-vibevoice'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "vibevoice"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
+            ubuntu-version: '2204'
           - build-type: 'cublas'
             cuda-major-version: "13"
             cuda-minor-version: "0"
@@ -459,6 +485,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
             ubuntu-version: '2204'
+          - build-type: 'l4t'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-nvidia-l4t-cuda-13-arm64-vibevoice'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            ubuntu-version: '2404'
+            backend: "vibevoice"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'l4t'
             cuda-major-version: "13"
             cuda-minor-version: "0"
@@ -669,6 +708,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
             ubuntu-version: '2204'
+          - build-type: 'hipblas'
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-rocm-hipblas-vibevoice'
+            runs-on: 'arc-runner-set'
+            base-image: "rocm/dev-ubuntu-22.04:6.4.3"
+            skip-drivers: 'false'
+            backend: "vibevoice"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
+            ubuntu-version: '2204'
           - build-type: 'hipblas'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -787,6 +839,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
             ubuntu-version: '2204'
+          - build-type: 'l4t'
+            cuda-major-version: "12"
+            cuda-minor-version: "0"
+            platforms: 'linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-nvidia-l4t-vibevoice'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+            skip-drivers: 'true'
+            backend: "vibevoice"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
+            ubuntu-version: '2204'
           - build-type: 'l4t'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -827,6 +892,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
             ubuntu-version: '2204'
+          - build-type: 'intel'
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-intel-vibevoice'
+            runs-on: 'arc-runner-set'
+            base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
+            skip-drivers: 'false'
+            backend: "vibevoice"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
+            ubuntu-version: '2204'
           - build-type: 'intel'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -1319,6 +1397,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
             ubuntu-version: '2204'
+          - build-type: ''
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64,linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-cpu-vibevoice'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "vibevoice"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
+            ubuntu-version: '2204'
   backend-jobs-darwin:
     uses: ./.github/workflows/backend_build_darwin.yml
     strategy:

Makefile

@@ -287,12 +287,14 @@ prepare-test-extra: protogen-python
 	$(MAKE) -C backend/python/diffusers
 	$(MAKE) -C backend/python/chatterbox
 	$(MAKE) -C backend/python/vllm
+	$(MAKE) -C backend/python/vibevoice
 
 test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/transformers test
 	$(MAKE) -C backend/python/diffusers test
 	$(MAKE) -C backend/python/chatterbox test
 	$(MAKE) -C backend/python/vllm test
+	$(MAKE) -C backend/python/vibevoice test
 
 DOCKER_IMAGE?=local-ai
 DOCKER_AIO_IMAGE?=local-ai-aio
@@ -389,6 +391,9 @@ backends/neutts: docker-build-neutts docker-save-neutts build
 backends/vllm: docker-build-vllm docker-save-vllm build
 	./local-ai backends install "ocifile://$(abspath ./backend-images/vllm.tar)"
 
+backends/vibevoice: docker-build-vibevoice docker-save-vibevoice build
+	./local-ai backends install "ocifile://$(abspath ./backend-images/vibevoice.tar)"
+
 build-darwin-python-backend: build
 	bash ./scripts/build/python-darwin.sh
 
@@ -445,6 +450,9 @@ docker-save-kitten-tts: backend-images
 docker-save-chatterbox: backend-images
 	docker save local-ai-backend:chatterbox -o backend-images/chatterbox.tar
 
+docker-save-vibevoice: backend-images
+	docker save local-ai-backend:vibevoice -o backend-images/vibevoice.tar
+
 docker-build-neutts:
 	docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:neutts -f backend/Dockerfile.python --build-arg BACKEND=neutts ./backend
 
@@ -523,10 +531,13 @@ docker-build-bark:
 docker-build-chatterbox:
 	docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:chatterbox -f backend/Dockerfile.python --build-arg BACKEND=chatterbox ./backend
 
+docker-build-vibevoice:
+	docker build --progress=plain --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:vibevoice -f backend/Dockerfile.python --build-arg BACKEND=vibevoice ./backend
+
 docker-build-exllama2:
 	docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:exllama2 -f backend/Dockerfile.python --build-arg BACKEND=exllama2 .
 
-docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-transformers docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-bark docker-build-chatterbox docker-build-exllama2
+docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-transformers docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-bark docker-build-chatterbox docker-build-vibevoice docker-build-exllama2
 
 ########################################################
 ### END Backends

backend/index.yaml

@@ -105,7 +105,7 @@
   capabilities:
     nvidia: "cuda12-rfdetr"
     intel: "intel-rfdetr"
     #amd: "rocm-rfdetr"
     nvidia-l4t: "nvidia-l4t-arm64-rfdetr"
     default: "cpu-rfdetr"
     nvidia-cuda-13: "cuda13-rfdetr"
@@ -390,6 +390,28 @@
     nvidia-cuda-12: "cuda12-chatterbox"
     nvidia-l4t-cuda-12: "nvidia-l4t-arm64-chatterbox"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-chatterbox"
+- &vibevoice
+  urls:
+    - https://github.com/microsoft/VibeVoice
+  description: |
+    VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech.
+  tags:
+    - text-to-speech
+    - TTS
+  license: mit
+  name: "vibevoice"
+  alias: "vibevoice"
+  capabilities:
+    nvidia: "cuda12-vibevoice"
+    intel: "intel-vibevoice"
+    amd: "rocm-vibevoice"
+    nvidia-l4t: "nvidia-l4t-vibevoice"
+    default: "cpu-vibevoice"
+    nvidia-cuda-13: "cuda13-vibevoice"
+    nvidia-cuda-12: "cuda12-vibevoice"
+    nvidia-l4t-cuda-12: "nvidia-l4t-vibevoice"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-vibevoice"
+  icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4
 - &piper
   name: "piper"
   uri: "quay.io/go-skynet/local-ai-backends:latest-piper"
@@ -967,7 +989,7 @@
   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"
@@ -1253,7 +1275,7 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-diffusers"
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-diffusers
   ## exllama2
 - !!merge <<: *exllama2
   name: "exllama2-development"
   capabilities:
@@ -1571,3 +1593,86 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-chatterbox"
   mirrors:
     - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-chatterbox
+## vibevoice
+- !!merge <<: *vibevoice
+  name: "vibevoice-development"
+  capabilities:
+    nvidia: "cuda12-vibevoice-development"
+    intel: "intel-vibevoice-development"
+    amd: "rocm-vibevoice-development"
+    nvidia-l4t: "nvidia-l4t-vibevoice-development"
+    default: "cpu-vibevoice-development"
+    nvidia-cuda-13: "cuda13-vibevoice-development"
+    nvidia-cuda-12: "cuda12-vibevoice-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-vibevoice-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-vibevoice-development"
+- !!merge <<: *vibevoice
+  name: "cpu-vibevoice"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-vibevoice"
+  mirrors:
+    - localai/localai-backends:latest-cpu-vibevoice
+- !!merge <<: *vibevoice
+  name: "cpu-vibevoice-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-vibevoice"
+  mirrors:
+    - localai/localai-backends:master-cpu-vibevoice
+- !!merge <<: *vibevoice
+  name: "cuda12-vibevoice"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-vibevoice"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-vibevoice
+- !!merge <<: *vibevoice
+  name: "cuda12-vibevoice-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-vibevoice"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-vibevoice
+- !!merge <<: *vibevoice
+  name: "cuda13-vibevoice"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-vibevoice"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-vibevoice
+- !!merge <<: *vibevoice
+  name: "cuda13-vibevoice-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-vibevoice"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-vibevoice
+- !!merge <<: *vibevoice
+  name: "intel-vibevoice"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-vibevoice"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-vibevoice
+- !!merge <<: *vibevoice
+  name: "intel-vibevoice-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-vibevoice"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-vibevoice
+- !!merge <<: *vibevoice
+  name: "rocm-vibevoice"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-vibevoice"
+  mirrors:
+    - localai/localai-backends:latest-gpu-rocm-hipblas-vibevoice
+- !!merge <<: *vibevoice
+  name: "rocm-vibevoice-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-vibevoice"
+  mirrors:
+    - localai/localai-backends:master-gpu-rocm-hipblas-vibevoice
+- !!merge <<: *vibevoice
+  name: "nvidia-l4t-vibevoice"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-vibevoice"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-vibevoice
+- !!merge <<: *vibevoice
+  name: "nvidia-l4t-vibevoice-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-vibevoice"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-vibevoice
+- !!merge <<: *vibevoice
+  name: "cuda13-nvidia-l4t-arm64-vibevoice"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-vibevoice"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-vibevoice
+- !!merge <<: *vibevoice
+  name: "cuda13-nvidia-l4t-arm64-vibevoice-development"
+  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

backend/python/vibevoice/Makefile

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