About ChatTTS
The 2noise project publishes ChatTTS, a generative speech model designed for daily dialogue. It turns text into natural-sounding conversational speech and is aimed especially at dialogue scenarios such as the voice of an LLM-powered assistant.
Supported languages are English and Chinese, with more planned. The repository contains the algorithm infrastructure and simple examples, while end-user products built on top of the model are collected in a community-maintained index called Awesome-ChatTTS. The model is implemented in Python with PyTorch and torchaudio, and the README is translated into several languages. The project highlights conversational speech with control over prosodic details such as laughter and pauses.
The code is released under AGPL-3.0 and runs on your own hardware, typically with a GPU for good speed. The model weights may carry separate terms from the code, so review those terms before any commercial use.
Key features
- Text-to-speech optimized for dialogue
- English and Chinese support
- Control over laughter and pauses
- PyTorch-based Python implementation
- Suited to LLM assistant voices
- Community ecosystem via Awesome-ChatTTS
Good fit for
- →Voice for LLM assistants
- →Generating conversational narration
- →Research on dialogue speech synthesis
- Built with
- Python
- Tags
- text-to-speech
- tts
- chattts
- speech-synthesis
- pytorch
- llm
- python
ChatTTS: questions and answers
- What is ChatTTS used for?
- ChatTTS from 2noise is a generative text-to-speech model tuned for conversational dialogue, such as LLM assistant replies, in English and Chinese. It is a good fit for voice for LLM assistants, generating conversational narration and research on dialogue speech synthesis.
- Is ChatTTS open source?
- Yes. ChatTTS is open source under the AGPL-3.0 licence. Its source code is on GitHub at 2noise/ChatTTS and is written mainly in Python.
- Is ChatTTS free?
- Yes. ChatTTS is open source, so the software itself is free to use.
- What is ChatTTS an alternative to?
- ChatTTS is an open-source alternative to ElevenLabs, Murf AI and Speechify. Other open-source alternatives to ElevenLabs include Piper.
- Is ChatTTS actively maintained?
- The most recent commit to ChatTTS was on 10 April 2026, and the latest release is v0.2.5, published on 10 April 2026. The project has 40k stars on GitHub.
Open-source alternatives to ChatTTS
See all
Piper
AI Tools
Fast and local neural text-to-speech engine
GPL-3.0vs ElevenLabs★ 5.7kPodcastfy
AI Tools
An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal
Apache-2.0vs NotebookLM★ 6.6k
Aider
AI Tools
aider is AI pair programming in your terminal
Apache-2.0vs Claude Code★ 49k
Self-Operating Computer
AI Tools
A framework to enable a multimodal model to operate a computer.
MIT★ 10k
AutoGPT
AI Tools
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission i
OSSvs Manus★ 188k
ComfyUI
AI Tools
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes inte
GPL-3.0vs Midjourney★ 136k
SaaS alternatives to ChatTTS
See all
ElevenLabs
AI Tools
Text-to-speech, voice cloning, dubbing and speech-to-text with an API
SaaS
Murf AI
AI Tools
Text-to-speech studio for voiceovers with a library of AI voices
SaaS
Speechify
AI Tools
Reads text, documents and web pages aloud with natural-sounding AI voices
SaaS
Audixa AI
AI Tools
Text-to-speech API and studio that generates realistic human-like voices
SaaS
BritishAccent
AI Tools
AI text-to-speech tool that generates British English audio in multiple UK accents, with voice cloning
SaaS
CopyKitten
AI Tools
Discord bot that clones a voice and generates speech with it
SaaS
