VoiceStudio
11,000Download

Open Source AI Voice Studio

fully-local voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages

curl -fsSL https://voicestudio.sh/install | sh

Desktop

WorkflowStudio

Users <3 VoiceStudio

Observed 21 Aug 2026

GitHub stars
11,000
Downloads + pulls
Release
v0.5.0
Recognition
Trendshift Repository of the Daydebpalash/VoiceStudio — Trendshift Repository Of The Day

Creators. Developers. Teams.

  • Creators

    Voiceovers, dubs, transcripts, voice design.

    Download

  • Developers

    OpenAI-compatible local API.

    Quickstart

  • Teams

    Commercial rights and hosted access. Pro is enquiry-only; Cloud is in early access.

    VoiceStudio Pro

Desktop field manual

From download to finished audio.

Screen-by-screen guides for the local app, written around the controls you will actually see.

Browse all UI guides
  1. Make your first voiceInstall an engine, choose a voice, and turn a short script into audio.5 min · first run
  2. Clone or design a voiceStart with a clean sample—or describe a new voice from scratch.voice workspace
  3. Dub a videoTranscribe, translate, cast speakers, generate, and export.six-stage workflow

What you're downloading

13 screens, captured in-app

  • The Launchpad home screen with cards for each workflow: voice clone, voice design, video dubbing, stories, audiobook, voice gallery, and transcripts.
    Launchpad
  • The Studio workspace with a script editor, style controls, and a synthesize audio action.
    Studio
  • The Voice Gallery with ready-made voice cards, category filters, and per-voice preview and use-voice actions.
    Voice Gallery
  • The Voice Design screen where a voice is described in text and generated with style and pitch controls.
    Voice Design
  • The Voice Clone screen with record and upload paths for creating a voice from a short sample.
    Voice Clone
  • The Dubbing editor with source audio waveform, per-speaker transcript rows, and language columns.
    Dubbing
  • The Projects library where generated audio and dubs are organized.
    Projects
  • The OpenAPI reference for the local OpenAI-compatible audio API, with client library snippets.
    Local API
  • The Model Catalogue with the engine compatibility matrix listing speech models with status, compute support, and install actions.
    Model Catalogue
  • Switching the active speech engine from the app header, with a confirmation toast, without leaving the current screen.
    Quick engine switch
  • The Logs console streaming model load and synthesis events.
    Logs
  • The Settings screen with the models directory, cache location, and Hugging Face mirror configuration.
    Settings
  • The Updates screen showing the in-app changelog and current release.
    Updates

Download VoiceStudio

Local. No account. Support varies.

Download