Clone a voice, dictate anywhere, and give agents a voice

Made by Jamie Pine

A local voice studio that covers both halves of speech: going out and coming in.

It clones a voice from a short sample or uses more than fifty preset voices, generates speech in 23 languages across seven different engines, and adds effects and expressive tags. Coming the other way, a global hotkey dictates into any text field on your machine. It also exposes a single tool call over MCP, so an AI assistant that supports it can speak back to you in a voice you chose. The project says models, voice data and recordings never leave your machine.

Can I use this?

Mac or Windows app

You'll need A Mac, Windows or Linux computer · Setup needed

Worth knowing Running seven speech engines and a bundled language model locally is not free of hardware cost, and quality and speed vary by engine. Cloning a voice from a sample is exactly the capability that makes impersonation easy, so whose voice you clone matters legally as well as ethically. Which engines and languages are available in a given build is the project’s list, not a guarantee. MIT licence. BuildTube has not run or verified this software.

Why it's here

Not trending this week

Last seen on the GitHub trending list on 20 September 2026. It stays on BuildTube so you can still find it.

56,496 people have starred it on GitHub.

Numbers checked on 6 October 2026; not refreshed since.

Behind it

See the code on GitHub

BuildTube has not run or verified this project. Everything above is written from what the creator published.

Made this?