Local AI voice studio to clone voices and dictate text
Free alternative to ElevenLabs · Descript
Voicebox lets you clone voices from short audio clips and generate speech across 23 languages. It also works as a system-wide dictation tool using hotkeys to transcribe what you speak into text. Everything runs completely on your own machine without sending data to the cloud.
Requires local compute resources; Linux currently requires building from source.
Not sure how to install, or if it’s safe? Read the beginner guide
Yes, Voicebox is completely free and open-source under the MIT license, running entirely on your machine without requiring paid API keys or cloud subscriptions.
It is open source (MIT license) with 60,588 GitHub stars, last updated 2026-10-07. Download only from the official link on this page, and scan the file before installing: see the safety checklist in our beginner guide.
Yes, both voice generation and system-wide dictation run completely on your local computer, meaning no audio data is ever sent to the cloud.
Compiled from the project README. 60,588 GitHub stars (2026-11-13) · License MIT · Last update 2026-10-07