Last updated 07-02-2026
Category:
Reviews:
Join thousands of AI enthusiasts in the World of AI!
ChatTTS
ChatTTS is an open-source text-to-speech model built for dialogue. The 2Noise team trained it on over 100,000 hours of Chinese and English speech so it sounds natural in back-and-forth conversation, not just scripted narration.
What sets it apart is prosody control at a granular level. The model can layer in laughter, pauses, and interjections, and it handles multiple speakers in a single session. That makes it a fit for LLM assistants, conversational audio, and dialogue-heavy multimedia.
Developers install it via pip or clone the GitHub repo. The open-source release on Hugging Face is a 40,000-hour base model under AGPLv3+. The team positions it for research and dialogue use cases, with contact at [email protected] for roadmap questions.
Shapes laughter, pauses, and interjections into synthesized speech
Runs multi-speaker dialogue from a single inference call
Trained on 100,000+ hours of Chinese and English audio
Streams audio output for real-time playback
Install via pip or pull weights from Hugging Face
Open-source with a large GitHub community and active development by 2Noise.
Fine-grained prosody control including laughter, pauses, and interjections.
Supports streaming inference, batching, and multi-speaker dialogue.
Available on PyPI and Hugging Face for straightforward local setup.
Licensed for academic and research use, not commercial projects.
Supports only English and Chinese, with no additional languages announced.
Requires a local Python environment; GPU hardware is recommended for faster generation.
The official 2noise.com site is minimal, so most documentation lives on GitHub.
Is ChatTTS free to use?
Yes. ChatTTS is open-source under AGPLv3+. You can install it with pip or clone the repository from GitHub at no cost.
What languages does ChatTTS support?
ChatTTS supports English and Chinese. The main model was trained on over 100,000 hours of audio data in both languages.
Can ChatTTS be used for commercial projects?
No. ChatTTS is intended for academic and research use only. The Hugging Face model card and project documentation explicitly restrict commercial and legal use.
How do I install ChatTTS?
Run pip install ChatTTS for the stable PyPI release, or pip install git+https://github.com/2noise/ChatTTS for the latest GitHub version. Model weights are available on Hugging Face at 2Noise/ChatTTS.
Where can I download the ChatTTS model weights?
The open-source 40,000-hour base model is hosted on Hugging Face at huggingface.co/2Noise/ChatTTS. Clone the GitHub repo and load models with the ChatTTS Python package.
What audio sample rate does ChatTTS output?
ChatTTS outputs audio at a 24,000 Hz sample rate. Generated waveforms can be saved with torchaudio or played back directly in Python notebooks.