hsiang

What it is OpenAI-compatible Text-to-Speech API powered by CosyVoice 3 (Alibaba FunAudioLLM). State-of-the-art Chinese TTS with 18 dialects, 9 languages, built-in voices, instruction-based control, and zero-shot voice cloning. No bloat — just the model served via FastAPI. Exposes /v1/audio/speech (OpenAI-compatible TTS), /v1/audio/speech/clone (voice cloning), /v1/voices, /docs (Swagger), /health Template details App name: CosyVoice3-API Template URL: https://raw.githubusercontent.com/hsiang-han/unraid_templates/main/templates/cosyvoice3-api.xml Icon URL: https://raw.githubusercontent.com/hsiang-han/unraid_templates/main/assets/cosyvoice3-api-icon.png Project URL: https://github.com/hsiang-han/CosyVoice3-API Support URL: https://github.com/hsiang-han/CosyVoice3-API/issues Container image strategy Repository (GPU only): ghcr.io/hsiang-han/cosyvoice3-api:latest Extra Parameters: --gpus all --shm-size=2g CUDA 12.8 — supports Blackwell (RTX 5060/5070/5090) and Ada GPUs Requires NVIDIA driver >= 570 Features Built-in voices: multiple Chinese/English/Japanese/Korean preset voices Instruction control: guide tone/emotion via text prompt Zero-shot voice cloning: clone any voice with just 3 seconds of reference audio FP16 inference: ~3-4GB VRAM (default), FP32: ~6-8GB VRAM Default mappings / settings Port: 8080 Host path: /mnt/user/appdata/cosyvoice3-api/models → /root/.cache/modelscope/hub API docs: http://[IP]:[PORT:8080]/docs First start downloads model (~2GB), subsequent starts are fast Environment variables MODEL_DIR = FunAudioLLM/Fun-CosyVoice3-0.5B-2512 — ModelScope model ID FP16 = true — Half-precision inference, reduces VRAM by ~50%. Set to false only if you experience quality issues. PORT = 8080 — Internal API server port NVIDIA_VISIBLE_DEVICES = all — GPU selection Usage # English TTS curl -X POST http://YOUR-UNRAID-IP:8080/v1/audio/speech \ -F "input=Hello world, this is a test" \ -F "voice=English Female" \ --output english.wav # Chinese TTS curl -X POST http://YOUR-UNRAID-IP:8080/v1/audio/speech \ -F "input=你好，世界" \ -F "voice=中文女" \ --output chinese.wav # Instruction control (English) curl -X POST http://YOUR-UNRAID-IP:8080/v1/audio/speech \ -F "input=What a beautiful day" \ -F "voice=English Female" \ -F "instruct_text=Say it happily and energetically" \ --output happy_en.wav # Instruction control (Chinese) curl -X POST http://YOUR-UNRAID-IP:8080/v1/audio/speech \ -F "input=今天天气真好" \ -F "voice=中文女" \ -F "instruct_text=用开心的语气说" \ --output happy_zh.wav # Voice cloning (3s reference audio) curl -X POST http://YOUR-UNRAID-IP:8080/v1/audio/speech/clone \ -F "input=This is the cloned voice" \ -F "prompt_text=Text spoken in the reference audio" \ -F "[email protected]" \ --output cloned.wav # List available voices curl http://YOUR-UNRAID-IP:8080/v1/voicesWorks with any OpenAI-compatible TTS client.

What it isPure OpenAI-compatible Speech-to-Text API powered by Qwen3-ASR (Alibaba Qwen). State-of-the-art accuracy for Chinese (22 dialects), English, and 50+ languages. No bloat — just the model served via vLLM. Exposes /v1/audio/transcriptions (OpenAI-compatible), /docs (Swagger), /health Template detailsApp name: Qwen3-ASR-API Template URL: https://raw.githubusercontent.com/hsiang-han/unraid_templates/main/templates/qwen3-asr-api.xml Icon URL: https://raw.githubusercontent.com/hsiang-han/unraid_templates/main/assets/qwen3-asr-api-icon.png Project URL: https://github.com/hsiang-han/qwen3-asr-api Support URL: https://github.com/hsiang-han/qwen3-asr-api/issues Container image strategyRepository (GPU only): ghcr.io/hsiang-han/qwen3-asr-api:latest Extra Parameters: --gpus all --shm-size=4g CUDA 12.8 — supports Blackwell (RTX 5060/5070/5090) and Ada GPUs Requires NVIDIA driver >= 570 Model selectionSwitch via MODEL_ID environment variable (restart required): Qwen/Qwen3-ASR-0.6B (default) — ~2-3GB VRAM, RTFx 166, low latency Qwen/Qwen3-ASR-1.7B — ~4-6GB VRAM, RTFx 148, best accuracy Default mappings / settingsPort: 8000 Host path: /mnt/user/appdata/qwen3-asr-api/models → /root/.cache/huggingface API docs: http://[IP]:[PORT:8000]/docs First start downloads model (~1-3GB), subsequent starts are fast Environment variablesMODEL_ID = Qwen/Qwen3-ASR-0.6B — Model to serve GPU_MEMORY_UTILIZATION = 0.8 — GPU memory fraction (0.0-1.0) NVIDIA_VISIBLE_DEVICES = all — GPU selection MAX_MODEL_LEN = 8192 — Max sequence length for KV cache. Default value can supports ~10 min audio. Lower to save VRAM, raise for longer audio. Usagecurl -X POST http://YOUR-UNRAID-IP:8000/v1/audio/transcriptions -F "[email protected]" -F "model=qwen3-asr" Works with any OpenAI-compatible client.

The container runs as a non-root user appuser (UID 1000). If the mounted host directories are not owned by UID 1000, the container cannot write to them, and you may see an error like: PermissionError: [Errno 13] Permission denied: 'api/src/models/v1_1_zh' Fix (run once in the Unraid terminal before first deployment): ``` # 1. Create mount directories mkdir -p /mnt/user/appdata/kokoro-fastapi-zh/models/v1_1_zh mkdir -p /mnt/user/appdata/kokoro-fastapi-zh/voices/v1_1_zh # 2. Set owner to UID 1000 (container appuser) chown -R 1000:1000 /mnt/user/appdata/kokoro-fastapi-zh # 3. Set read/write permissions chmod -R 775 /mnt/user/appdata/kokoro-fastapi-zh ``` Note: The Unraid terminal runs as root by default, so you can execute these commands directly. This is only required once before the first deployment.

What it is OpenAI-compatible TTS API based on hexgrad/Kokoro-82M-v1.1-zh (Chinese optimized TTS model hexgrad/Kokoro-82M-v1.1-zh · Hugging Face ) Exposes: /v1/audio/speech docs (Swagger) web (web UI) Template details App name: Kokoro-FastAPI-zh Template URL: https://raw.githubusercontent.com/hsiang-han/unraid_templates/main/templates/kokoro-fastapi-zh.xml Icon URL: https://raw.githubusercontent.com/hsiang-han/unraid_templates/main/assets/unraid-icon.png Project URL: https://github.com/hsiang-han/Kokoro-FastAPI-zh Support URL: https://github.com/hsiang-han/Kokoro-FastAPI-zh/issues Container image strategy Default repository (CPU): ghcr.io/hsiang-han/kokoro-fastapi-zh-cpu:latest Optional NVIDIA GPU mode: Change Repository to ghcr.io/hsiang-han/kokoro-fastapi-zh-gpu:latest Set USE_GPU=true Add Extra Parameters: --gpus=all --runtime=nvidia Default mappings / settings Port: 8880 Host paths: /mnt/user/appdata/kokoro-fastapi-zh/models -> /app/api/src/models /mnt/user/appdata/kokoro-fastapi-zh/voices -> /app/api/src/voices API docs: http://[IP]:[PORT:8880]/docs Web UI: http://[IP]:[PORT:8880]/web

Thanks for the efforts maintaining this image. Is there any plan to update to ComfyUI v0.6?