OmniVoice
by k2-fsa
Zero-shot TTS covering 600+ languages, with voice cloning from a short clip and voice design by speaker attributes.
Voiceover (text-to-speech) Code libraryOpen source
1. Price: huggingface.co/k2-fsa/OmniVoice
Open weights, free to download.
huggingface.co/k2-fsa/OmniVoiceNo quote yet: price is read from the official pages.
2. Commercial use: huggingface.co/k2-fsa/OmniVoice
“The pre-trained model is licensed under the CC-BY-NC due to constraints from its training data (e.g., Emilia).”
The pre-trained model is under CC-BY-NC, which rules out commercial use.
huggingface.co/k2-fsa/OmniVoice3. Credit the author: huggingface.co
“prominently display “Built with Higgs Materials licensed from Boson AI USA, Inc., Copyright Boson AI USA, Inc., All Rights Reserved”
Built with Higgs Materials licensed from Boson AI USA, Inc., Copyright Boson AI USA, Inc., All Rights Reserved and Meta Llama 3 licensed under the Meta Llama 3 Community License, Copyright Meta Platforms, Inc., All Right Reserved
huggingface.co4. Agent access: github.com/k2-fsa/OmniVoice
An agent can install it by itself with pip install omnivoice.
github.com/k2-fsa/OmniVoiceLicense checked Nov 10, 2026 against 2 official pages. Tap a verdict to see its source. How we checked Report an error
OmniVoice: speech in 600+ languages, non-commercial
OmniVoice is a free AI model that reads text aloud in more than 600 languages. It can copy a voice from a few seconds of recorded speech, or make a new voice from a short description like "female, low pitch". The program code is open, but the model itself may only be used for non-commercial work.
Where you can use it
Speech for rare languages in research
Make spoken audio for a language that common voice tools skip, for a study, a school project or a language archive.
Your own voice from a short clip
Record 3 to 10 seconds of your voice, add what you said, and the model reads new text in that voice. Copying someone else's voice without permission is forbidden.
A new voice from a description
No recording needed. Describe the voice by gender, age, pitch, accent or a whisper, and the model makes one.
Laughs, sighs and exact pronunciation
Put a laugh or a sigh into the text, or spell out how a word should sound, so lines in a story or game feel natural.
Many audio lines in one run
Turn a long list of lines into audio files at once, for example all phrases of a language course, spread over several graphics cards.
Trying it without code
Start a local web page where you type text, upload a voice sample and listen, before deciding to build anything.
As reported by k2-fsa: Over 600 languages; Real-time factor as low as 0.025 (40x faster than real time).
OmniVoice popularity
Downloads from pypistats.org, stars from GitHub, checked Nov 19, 2026. How the Gid Score is calculated
How to start
Tell your AI assistant
“For a non-commercial research project, install omnivoice 0.2.1 in a fresh virtual environment (PyTorch 2.8 for my machine, device_map "mps" on a Mac), and write a script that reads lines.txt and saves one WAV per line with the voice "female, low pitch, british accent".”
Show codeStep 1 or Step 2
Install PyTorch for your machine first (the README shows the commands for NVIDIA, Apple Silicon and Intel), then install OmniVoice from PyPI.
pip install torch==2.8.0 torchaudio==2.8.0
pip install omnivoice
Generate speech from the command line; the model downloads from Hugging Face on first use.
omnivoice-infer --model k2-fsa/OmniVoice \
--text "This is a test for text to speech." \
--instruct "male, British accent" \
--output hello.wav
Mistakes to avoid
The Apache license covers the code only; the model card puts the weights under CC-BY-NC.
The README example targets NVIDIA cards.
Longer samples slow it down and can lower quality; a sample in another language adds an accent.
The README offers third-party mirrors only as a workaround for connection trouble.
License
Code Apache-2.0; pre-trained model CC-BY-NC (model card); audio tokenizer under the Boson Higgs Audio 2 Community License. Non-commercial only. The code is Apache-2.0, but the model is CC-BY-NC because of its training data, and a bundled part adds Boson AI terms with a credit line and a 100,000-user cap.
“The pre-trained model is licensed under the CC-BY-NC due to constraints from its training data (e.g., Emilia).” huggingface.co/k2-fsa/OmniVoice
“prominently display “Built with Higgs Materials licensed from Boson AI USA, Inc., Copyright Boson AI USA, Inc., All Rights Reserved” huggingface.co
“The pre-trained model is licensed under the CC-BY-NC due to constraints from its training data (e.g., Emilia).” huggingface.co/k2-fsa/OmniVoice
Non-commercial sharing only, with the license agreements and the Meta Llama 3 notice kept in the copies.
“You must retain in all copies of the Llama Materials that you distribute and as set forth above, include the following attribution notice within a “Notice” text file distributed as a part of such copies” huggingface.co
“The pre-trained model is licensed under the CC-BY-NC due to constraints from its training data (e.g., Emilia).” huggingface.co/k2-fsa/OmniVoice
AllowedWith conditionsNot allowedNot stated or not checked yet
Is OmniVoice free for commercial use? The full answer Not legal advice. Check the license page before you ship.
For your agent
License rules tell your agent what it may do with OmniVoice. Paste them into your prompt or AGENTS.md.
- OmniVoice (Voiceover (text-to-speech)). Zero-shot TTS covering 600+ languages, with voice cloning from a short clip and voice design by speaker attributes. Price: free; non-commercial only; credit required; cannot ship inside an app.
Connect: PyPI omnivoice.
Rule: The code is Apache-2.0; the audio tokenizer shipped with the weights is under the Boson Higgs Audio 2 Community License (Llama 3 based).
Rule: Products or services above 100,000 annual active users need an expanded license from Boson AI.
Rule: A product or service using it must show "Built with Higgs Materials licensed from Boson AI" and follow the Llama 3 acceptable-use policy.
Rule: Outputs may not be used to improve other large language models.
Rule: The pre-trained OmniVoice model is CC-BY-NC (non-commercial), per its model card.
License: https://huggingface.co/k2-fsa/OmniVoice/blob/main/audio_tokenizer/LICENSE (checked 2026-11-10; details: https://agentgid.com/assets/omnivoice/)
Agent installs a package or loads it from a CDN.
pip install omnivoiceBuilt with Higgs Materials licensed from Boson AI USA, Inc., Copyright Boson AI USA, Inc., All Rights Reserved and Meta Llama 3 licensed under the Meta Llama 3 Community License, Copyright Meta Platforms, Inc., All Right ReservedAlternatives
OmniVoice This page
Pick CosyVoice 3 for a voice cloning model whose card lists Apache-2.0, when you need commercial use and its 9 languages are enough.
Pick Chatterbox for an MIT-licensed cloning model in 23 languages with a built-in audio watermark.
Pick Qwen3-TTS for preset voices and voice design from a text prompt in 10 languages.
Local desktop app for voice cloning, voice design, video dubbing, dictation and transcription in 646 languages, with a local API and an MCP server for agents.
Long-form multi-speaker TTS for podcast-style dialogue, up to 90 minutes and 4 speakers, in English and Chinese.
Questions
Can I use OmniVoice in a paid app or for client work?
No. The model card says the pre-trained model is CC-BY-NC, a non-commercial license; only the code is Apache-2.0.
Do I have to type what is said in my voice sample?
No. If you leave out ref_text, the model transcribes the sample with Whisper by itself.
Does it run on a Mac?
Yes. The README gives an Apple Silicon install and says to use device_map="mps".
Can I reuse a cloned voice later without the sample?
Yes. Encode the sample once, save it as a file, and load it in later sessions.
Are numbers read correctly?
Write them as words, or pass normalize_text=True after installing the omnivoice[tn] extra.