What it does
VoiceStudio is a desktop app that brings many voice tools together. You can copy a voice from a short, clean recording, design a new voice, turn text into speech, and dub a video with timed speech in another language.
It can also type what you say through a small floating dictation window, write out transcripts, and build stories and audiobooks. Its makers say it covers hundreds of languages, runs on your own hardware, and only uses online services if you choose to. Usage analytics are only collected with your consent.
It works best with an NVIDIA graphics card or an Apple Silicon Mac, but can also run more slowly on an ordinary computer's processor. It offers a local connection that other apps and AI assistants can use.
Who it's for
Video makers, podcasters, writers and anyone who wants private voice tools without an online subscription.
Can I use it without coding?
Yes. There are installers for Mac, Windows and Linux. Voice models download inside the app, and a powerful computer helps. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Mac, Windows, Linux
- Computer
- An ordinary computer is fine
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
- Download the installer for your computer from the project's releases page.
- Open Voice cloning, choose a voice or add a clean recording, and type your text.
- Install the required model when prompted, then generate the audio.
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 (AGPL-3.0): Free to use; if you run a changed version as an online service, you must share your source code.
- More on staying safe