debpalash / VoiceStudio

Voice cloning · dubbing · transcription · AGPL-3.0

Your voice.
Your hardware.

Open-source voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation in 646 languages. The project states it plainly: local workflows run on your hardware, remote services are optional, and usage analytics requires consent.

Read the source Download a release

Where the signal goes

the line is opt-in, not default

On your machine

Default. Powered by the bundled engine, or another from the catalog.

  • Voice cloning and voice design
  • Video dubbing with timed speech
  • Dictation via a floating widget
  • Transcription, stories, audiobooks, batch jobs
  • Local API and MCP for agents
  • Local speech models you install and manage

Only if you ask

Optional. Nothing here is required to use the app.

  • Optional remote workers
  • Optional remote services
  • Usage analytics — requires consent

Both columns are the project’s own wording. The right column is short on purpose — that is the product claim, not a gap in the feature list.

Create

  • Clone a voice or design your own
  • Dictate with a floating widget

Produce

  • Dub videos with timed speech
  • Stories, audiobooks & batch jobs

Connect

  • Local API & MCP for agents
  • Optional remote workers

Install is one command on macOS and Linux, and the installer preserves your settings, projects and models. The uninstall flag keeps your data. No quality score, latency figure or voice count beyond the published language number appears here.