Model reference · open weights
OmniVoice is an open-weight audio or speech model from k2-fsa, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
OmniVoice 🌍 OmniVoice is a massively multilingual zero-shot text-to-speech (TTS) model supporting over 600 languages. Built on a novel diffusion language model-style architecture, it delivers high-quality speech with superior inference speed, supporting voice cloning and voice design. - Paper: OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models - Repository: GitHub - Demo: Hugging Face Space - Colab: Google Colab Notebook Key Features - 600+ Languages Supported: The broadest language coverage among zero-shot TTS models. - Voice Cloning: State-of-the-art voice cloning quality from a short reference audio. - 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. Usage To get started, install the omnivoice library: We recommend using a fresh virtual environment (e.g., conda, venv, etc.) to avoid conflicts. Step 1: Install PyTorch See PyTorch official site for other versions installation. Step 2: Install OmniVoice Python API You can use OmniVoice for zero-shot voice cloning as follows: For more generation modes (e.g., voice design), functions (e.g., non-verbal symbols, pronunciation correction) and comprehensive usage instructions, see our GitHub Repository. Discussion & Communication You can directly discuss on GitHub Issues. You can also scan the QR code to join our wechat group or follow our wechat official account. Citation License Our code is released under the Apache 2.0 License. The pre-trained model is licensed under the CC-BY-NC due to constraints from its training data (e.g., Emilia). Disclaimer Users are strictly prohibited from using this model for unauthorized voice cloning, voice impersonation, fraud, scams, or any other illegal or unethical activities. All users shall ensure full compliance with applicable local laws, reg
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | k2-fsa |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 613M |
| Variants | 1 |
| Runs with | omnivoice |
| Based on | Qwen/Qwen3-0.6B |
| Released | 2026-03-30 |
| Popularity | 1M downloads / month |
| Likes | 1,321 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| OmniVoice | 613M | BF16 | ~1.4 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys omnivoice for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (omnivoice below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="omnivoice" -F file=@audio.mp3
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗