What it does
GPT-SoVITS is a text-to-speech tool with a web interface. Its makers say a 5-second voice sample is enough to produce speech in that voice, and that training on about 1 minute of audio makes the result sound closer.
It can speak in English, Japanese, Korean, Cantonese and Chinese, even if the sample was in a different language. It also includes helper tools to separate a voice from background music, cut recordings into training clips and transcribe Chinese speech.
Who it's for
Content creators, hobbyists and developers working on voiceovers, dubbing or custom voices.
Can I use it without coding?
With some setup. Windows users can download a ready-made package and double-click to start. Mac and Linux need a few install commands. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Windows, Mac, Linux
- 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
- On Windows, download the integrated package and double-click the start file to open the web interface.
- On Mac or Linux, run the project's install script, then start the web interface.
- Give it a short voice sample and type text to hear it spoken in that voice.
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 (MIT): Very permissive: free to use, change and share, including for business.
- More on staying safe