Plain-AyI
← All projects
Speech & audio

Real-Time Voice Cloning

A research project that turns typed text into speech in a voice learned from a few seconds of audio.

Research-backed

What it does

This project builds on a 2018 research paper. It makes a digital fingerprint of a voice from a short recording, then uses it to read out any text you type. It includes a simple desktop toolbox for trying it.

The author notes the project has aged, that many paid services now sound better, and points to newer open projects for higher quality.

Who it's for

Students and researchers interested in how speech synthesis works.

Can I use it without coding?

With some setup. Needs a few terminal commands to install and run on Windows or Linux. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Windows, Linux
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

  1. Install the ffmpeg audio tool and the uv Python tool.
  2. Start the toolbox, choosing the graphics card or ordinary processor option for your computer.
  3. Give it a few seconds of a voice, then type text for it to speak.

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.
  • No standard license listed. Check the GitHub page before using it for business.
  • More on staying safe

Where people are talking about it