k2-fsa /OmniVoice

High-Quality Voice Cloning TTS for 600+ Languages

★ 16,613⑂ 2,442👁 72⑃ 80● 219▤ 6
PythonApache-2.0Created 2026-03-31
More from this author
Download: 0.2.10.2.1 ↓0.2.12026-07-16
+12
Daily
16,613
stars
2,442
forks
72
watchers
80
prs
219
issues
6
releases

README

OmniVoice 🌍


  



  
   
  
   
  
   
  
   
  


OmniVoice is a state-of-the-art massively multilingual zero-shot text-to-speech (TTS) model supporting over 600 languages. Built on a novel diffusion language model-style architecture, it generates high-quality speech with superior inference speed, supporting voice cloning and voice design.

Contents: Key Features | Installation | Quick Start | Python API | Command-Line Tools | Training & Evaluation | Discussion | Citation

 Key Features

- 600+ Languages Supported: The broadest language coverage among zero-shot TTS models (full list).
- Voice Cloning: State-of-the-art voice cloning quality.
- Voice Design: Control voices via assigned speaker attributes (gender, age, pitch, dialect/accent, whisper, etc.).
- Fine-grained Control: Non-verbal symbols (e.g., [laughter]) and pronunciation correction via pinyin or phonemes.
- Fast Inference: RTF as low as 0.025 (40x faster than real-time).
- Diffusion Language Model-style Architecture: A clean, streamlined, and scalable design that delivers both quality and speed.

---

 Installation

Choose one of the following methods: pip or uv.

 pip

 We recommend using a fresh virtual environment (e.g., conda, venv, etc.) to avoid conflicts.

Step 1: Install PyTorch


NVIDIA GPU

bash
 Install pytorch with your CUDA version, e.g.
pip install torch==2.8.0+cu128 torchaudio==2.8.0+cu128 --extra-index-url https://download.pytorch.org/whl/cu128

 See PyTorch official site for other versions installation.




Apple Silicon

bash
pip install torch==2.8.0 torchaudio==2.8.0





Intel Arc GPU (XPU)

Intel Arc GPUs (Alchemist and Battlemage architectures) are supported via PyTorch's XPU backend.

1. Install the Intel GPU drivers for your OS.

2. Install PyTorch with XPU support from Intel's wheel index:

bash
pip install torch torchaudio --index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/


 See Intel's PyTorch XPU guide for version-specific instructions.

3. Verify the backend is working:

bash
python -c "import torch; print(torch.xpu.is_available(), torch.xpu.device_count())"


Notes:
- flash_attn is not available on XPU; the model automatically falls back to SDPA.
- Training with packed sequences (flex_attention) has partial XPU support; single-GPU SDPA training should work.
- Tested on Arc A310 (Alchemist, 4 GB) and Arc Pro B50 (Battlemage, 16 GB).



Step 2: Install OmniVoice (choose one)

bash
 From PyPI (stable release)
pip install omnivoice

 From the latest source on GitHub (no need to clone)
pip install git+https://github.com/k2-fsa/OmniVoice.git

 For development (clone first, editable install)
git clone https://github.com/k2-fsa/OmniVoice.git
cd OmniVoice
pip install -e .


 uv

Clone the repository and sync dependencies:

bash
git clone https://github.com/k2-fsa/OmniVoice.git
cd OmniVoice
uv sync


 Tip: Can use mirror with uv sync --default-index "https://mirrors.aliyun.com/pypi/simple"

---

 Quick Start

Try Omni

Top issues

Latest release

0.2.1 0.2.1 2026-07-16
What's Changed
 Add audio.cpp to community projects by @0xShug0 in https://github.com/k2-fsa/OmniVoice/pull/209
 Make flex_attention honor autocast (fixes silent fp32 attention, ~4x training slowdown) by @shuaills in https://github.com/k2-fsa/OmniVoice/pull/212
 Honor asr_model_name when the ASR model is loaded lazily by @HenryVarro666 in https://github.com/k2-fsa/OmniVoice/pull/221
 Add VoiceClonePrompt.save()/load() for cross-session voice reuse by @HenryVarro666 in https://github.com/k2-fsa/OmniVoice/pull/223
 Fix ASR model always loading on GPU 0; add asr_device option by @HenryVarro6

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON