Plain-AyI
← All projects
Speech & audio

ChatTTS

Turns text into natural, chatty-sounding speech in English and Chinese, with laughs and pauses.

What it does

ChatTTS is a text-to-speech model, AI that reads text aloud. It is designed for conversation, such as giving voice to an AI assistant, and supports multiple speakers.

It can add natural touches like laughter, pauses and filler words. It currently supports English and Chinese.

Its makers say they deliberately lowered the audio quality of the released model and added faint noise to make misuse harder.

Who it's for

Developers and researchers building voice features for chat apps.

Can I use it without coding?

Developers only. Installed and used through Python code. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

  1. Download the project and install its Python requirements.
  2. Launch the included web interface and type the text you want spoken.

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (AGPL-3.0): Free to use; if you run a changed version as an online service, you must share your source code.
  • More on staying safe

Where people are talking about it