Plain-AyI
← All projects
Speech & audio

VoxCPM

An open text-to-speech model that reads text aloud in 30 languages and can design or copy voices.

Research-backed

What it does

VoxCPM turns written text into natural-sounding speech. The latest version, VoxCPM2, supports 30 languages and several Chinese dialects, and outputs high-quality audio.

You can create a brand-new voice just by describing it, such as age, tone and mood, without any sample recording. You can also clone a voice from a short clip, and optionally steer its emotion and pace.

The model and code are released under the Apache-2.0 license, which allows commercial use. It can be used from Python, the command line or a simple web demo, and it can stream audio in real time on a strong graphics card. Its makers list risks and limitations in the README.

Who it's for

Developers, researchers and creators who need text-to-speech or custom voices in many languages.

Can I use it without coding?

With some setup. It installs with a Python command and includes a web demo, but runs best on a computer with a good graphics card. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Mac, Web browser
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Your choice: run it on your device or use an online service
API key
Not needed

Try it

  1. Try the online playground demo to hear it without installing anything.
  2. To run it yourself, install VoxCPM on a computer with a capable graphics card.
  3. Start its web demo and open it in your browser to type text and make speech.

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 (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it