feat(qwen-tts): add Qwen-tts backend

.github/workflows/backend.yml

@@ -105,6 +105,19 @@ 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-qwen-tts'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "qwen-tts"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "9"
@@ -353,6 +366,19 @@ 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-qwen-tts'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "qwen-tts"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "13"
             cuda-minor-version: "0"
@@ -431,6 +457,19 @@ jobs:
             backend: "vibevoice"
             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-qwen-tts'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            ubuntu-version: '2404'
+            backend: "qwen-tts"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
           - build-type: 'l4t'
             cuda-major-version: "13"
             cuda-minor-version: "0"
@@ -680,6 +719,19 @@ 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-qwen-tts'
+            runs-on: 'arc-runner-set'
+            base-image: "rocm/dev-ubuntu-24.04:6.4.4"
+            skip-drivers: 'false'
+            backend: "qwen-tts"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'hipblas'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -824,6 +876,19 @@ 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-qwen-tts'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+            skip-drivers: 'true'
+            backend: "qwen-tts"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2204'
           - build-type: 'l4t'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -890,6 +955,19 @@ 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-qwen-tts'
+            runs-on: 'arc-runner-set'
+            base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+            skip-drivers: 'false'
+            backend: "qwen-tts"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'intel'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -1343,6 +1421,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
+          - build-type: ''
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64,linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-cpu-qwen-tts'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "qwen-tts"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: ''
             cuda-major-version: ""
             cuda-minor-version: ""

.github/workflows/test-extra.yml

@@ -284,4 +284,23 @@ jobs:
       - name: Test pocket-tts
         run: |
           make --jobs=5 --output-sync=target -C backend/python/pocket-tts
-          make --jobs=5 --output-sync=target -C backend/python/pocket-tts test
+          make --jobs=5 --output-sync=target -C backend/python/pocket-tts test
+  tests-qwen-tts:
+    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 qwen-tts
+        run: |
+          make --jobs=5 --output-sync=target -C backend/python/qwen-tts
+          make --jobs=5 --output-sync=target -C backend/python/qwen-tts test

Dockerfile

@@ -10,7 +10,7 @@ ENV DEBIAN_FRONTEND=noninteractive
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
         ca-certificates curl wget espeak-ng libgomp1 \
-        ffmpeg libopenblas0 libopenblas-dev && \
+        ffmpeg libopenblas0 libopenblas-dev sox && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 

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/moonshine backends/pocket-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/moonshine backends/pocket-tts backends/qwen-tts
 
 GOCMD=go
 GOTEST=$(GOCMD) test
@@ -317,6 +317,7 @@ prepare-test-extra: protogen-python
 	$(MAKE) -C backend/python/vibevoice
 	$(MAKE) -C backend/python/moonshine
 	$(MAKE) -C backend/python/pocket-tts
+	$(MAKE) -C backend/python/qwen-tts
 
 test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/transformers test
@@ -326,6 +327,7 @@ test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/vibevoice test
 	$(MAKE) -C backend/python/moonshine test
 	$(MAKE) -C backend/python/pocket-tts test
+	$(MAKE) -C backend/python/qwen-tts test
 
 DOCKER_IMAGE?=local-ai
 DOCKER_AIO_IMAGE?=local-ai-aio
@@ -459,6 +461,7 @@ BACKEND_CHATTERBOX = chatterbox|python|.|false|true
 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
 
 # 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)
@@ -505,12 +508,13 @@ $(eval $(call generate-docker-build-target,$(BACKEND_CHATTERBOX)))
 $(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)))
 
 # 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-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 docker-build-moonshine docker-build-pocket-tts
+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 docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts
 
 ########################################################
 ### END Backends

README.md

@@ -298,6 +298,7 @@ LocalAI supports a comprehensive range of AI backends with multiple acceleration
 | **neutts** | Text-to-speech with voice cloning | CUDA 12/13, ROCm, CPU |
 | **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 |
 
 ### Image & Video Generation
 | Backend | Description | Acceleration Support |
@@ -319,8 +320,8 @@ 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, bark, neutts, vibevoice, pocket-tts | AMD Graphics |
-| **Intel oneAPI** | llama.cpp, whisper, stablediffusion, vllm, transformers, diffusers, rfdetr, rerankers, exllama2, coqui, kokoro, bark, vibevoice, pocket-tts | Intel Arc, Intel iGPUs |
+| **AMD ROCm** | llama.cpp, whisper, vllm, transformers, diffusers, rerankers, coqui, kokoro, bark, neutts, vibevoice, pocket-tts, qwen-tts | AMD Graphics |
+| **Intel oneAPI** | llama.cpp, whisper, stablediffusion, vllm, transformers, diffusers, rfdetr, rerankers, exllama2, coqui, kokoro, bark, vibevoice, pocket-tts, qwen-tts | Intel Arc, Intel iGPUs |
 | **Apple Metal** | llama.cpp, whisper, diffusers, MLX, MLX-VLM, bark-cpp | 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.) |

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"
@@ -428,6 +428,28 @@
     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
+- &qwen-tts
+  urls:
+    - https://github.com/QwenLM/Qwen3-TTS
+  description: |
+    Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning.
+  tags:
+    - text-to-speech
+    - TTS
+  license: apache-2.0
+  name: "qwen-tts"
+  alias: "qwen-tts"
+  capabilities:
+    nvidia: "cuda12-qwen-tts"
+    intel: "intel-qwen-tts"
+    amd: "rocm-qwen-tts"
+    nvidia-l4t: "nvidia-l4t-qwen-tts"
+    default: "cpu-qwen-tts"
+    nvidia-cuda-13: "cuda13-qwen-tts"
+    nvidia-cuda-12: "cuda12-qwen-tts"
+    nvidia-l4t-cuda-12: "nvidia-l4t-qwen-tts"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-qwen-tts"
+  icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4
 - &pocket-tts
   urls:
     - https://github.com/kyutai-labs/pocket-tts
@@ -973,7 +995,7 @@
   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"
@@ -1229,7 +1251,7 @@
   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:
@@ -1613,6 +1635,89 @@
   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
+## qwen-tts
+- !!merge <<: *qwen-tts
+  name: "qwen-tts-development"
+  capabilities:
+    nvidia: "cuda12-qwen-tts-development"
+    intel: "intel-qwen-tts-development"
+    amd: "rocm-qwen-tts-development"
+    nvidia-l4t: "nvidia-l4t-qwen-tts-development"
+    default: "cpu-qwen-tts-development"
+    nvidia-cuda-13: "cuda13-qwen-tts-development"
+    nvidia-cuda-12: "cuda12-qwen-tts-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-qwen-tts-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-qwen-tts-development"
+- !!merge <<: *qwen-tts
+  name: "cpu-qwen-tts"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-qwen-tts"
+  mirrors:
+    - localai/localai-backends:latest-cpu-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "cpu-qwen-tts-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-qwen-tts"
+  mirrors:
+    - localai/localai-backends:master-cpu-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "cuda12-qwen-tts"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-qwen-tts"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "cuda12-qwen-tts-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-qwen-tts"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "cuda13-qwen-tts"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-qwen-tts"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "cuda13-qwen-tts-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-qwen-tts"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "intel-qwen-tts"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-qwen-tts"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "intel-qwen-tts-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-qwen-tts"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "rocm-qwen-tts"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-qwen-tts"
+  mirrors:
+    - localai/localai-backends:latest-gpu-rocm-hipblas-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "rocm-qwen-tts-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-qwen-tts"
+  mirrors:
+    - localai/localai-backends:master-gpu-rocm-hipblas-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "nvidia-l4t-qwen-tts"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-qwen-tts"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "nvidia-l4t-qwen-tts-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-qwen-tts"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "cuda13-nvidia-l4t-arm64-qwen-tts"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-qwen-tts"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-qwen-tts
+- !!merge <<: *qwen-tts
+  name: "cuda13-nvidia-l4t-arm64-qwen-tts-development"
+  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
 ## pocket-tts
 - !!merge <<: *pocket-tts
   name: "pocket-tts-development"

backend/python/bark/requirements-intel.txt

@@ -1,8 +1,6 @@
---extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
-intel-extension-for-pytorch==2.8.10+xpu
-torch==2.3.1+cxx11.abi
-torchaudio==2.3.1+cxx11.abi
-oneccl_bind_pt==2.3.100+xpu
+--extra-index-url https://download.pytorch.org/whl/xpu
+torch
+torchaudio
 optimum[openvino]
 setuptools
 transformers

backend/python/chatterbox/requirements-intel.txt

@@ -1,7 +1,6 @@
---extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
-intel-extension-for-pytorch==2.3.110+xpu
-torch==2.3.1+cxx11.abi
-torchaudio==2.3.1+cxx11.abi
+--extra-index-url https://download.pytorch.org/whl/xpu
+torch
+torchaudio
 transformers
 numpy>=1.24.0,<1.26.0
 # https://github.com/mudler/LocalAI/pull/6240#issuecomment-3329518289

backend/python/common/libbackend.sh

@@ -398,7 +398,7 @@ function runProtogen() {
 # NOTE: for BUILD_PROFILE==intel, this function does NOT automatically use the Intel python package index.
 # you may want to add the following line to a requirements-intel.txt if you use one:
 #
-# --index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
+# --index-url https://download.pytorch.org/whl/xpu
 #
 # If you need to add extra flags into the pip install command you can do so by setting the variable EXTRA_PIP_INSTALL_FLAGS
 # before calling installRequirements.  For example:

backend/python/common/template/requirements-intel.txt

@@ -1,5 +1,4 @@
---extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
-intel-extension-for-pytorch==2.8.10+xpu
+--extra-index-url https://download.pytorch.org/whl/xpu
 torch==2.8.0
 oneccl_bind_pt==2.8.0+xpu
 optimum[openvino]