A generative speech model for daily dialogue.
About this project
ChatTTS is an open-source speech and audio project on GitHub: A generative speech model for daily dialogue. It covers speech and audio, the layer that turns text into voice, voice into text, or raw audio into something structured. It is maintained by 2noise and published as a public repository you can read, fork and run yourself.
On GitHub the repository is tagged agent, chat, chatgpt, chattts, chinese, chinese-language, english, english-language, gpt, llm, llm-agent and natural-language-inference, which is a fair summary of what it covers. Most deployments care about latency and voice quality, so the project usually ships both a batch path and a streaming or real-time one.
It is written mainly in Python and released under AGPL-3.0, a copyleft license — if you distribute it or run it as a public service, your derivative code has to be released. The last commit was on April 11, 2026, so development is moving, just not on a daily basis.
To try it, clone the repository and follow its README; that file is the canonical install guide. Because it runs on your own infrastructure, budget time for environment setup: dependencies, model weights and configuration usually take longer than the first successful run.
Key facts as recorded on GitHub: 40,013 stars; 4,245 forks; primary language Python; license AGPL-3.0; last commit on April 11, 2026; topics agent, chat, chatgpt, chattts, chinese, chinese-language.