← All projects
Speech & audio

Voicebox

A desktop voice studio that clones voices, reads text aloud and lets you dictate, all on your own computer.

Fast-rising

What it does

Voicebox is an app for working with AI voices. It can copy a voice from a few seconds of recorded audio, then read any text aloud in that voice, or use one of many preset voices. It supports many languages and several different speech engines.

It also works the other way: press a shortcut key and speak, and it types what you said into any app. A built-in editor lets you arrange several voices on a timeline for podcasts or stories, and AI coding tools can use it to speak to you.

Its makers say models and voice recordings never leave your machine.

Who it's for

Podcasters, writers, creators and anyone who wants private text-to-speech or dictation.

Can I use it without coding?

Yes. There are downloadable apps for Mac and Windows; Linux users currently need to build it themselves. New to this? Start here.

Can I run it?

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

Try it

  1. Download the installer for Mac or Windows from the project's website or releases page.
  2. Open Voicebox and record or upload a short voice sample to create a voice profile.
  3. Type some text and generate speech in that voice.
Official download page

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 or the official download page above. 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