VoiceStudio
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation i
What is VoiceStudio?
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
Overview of VoiceStudio
What it is
VoiceStudio is an open-source, fully-local alternative to ElevenLabs. It provides voice cloning, voice design, video dubbing, dictation, transcription, and audiobook creation in 646 languages. It runs locally on the user's hardware, with optional remote services and usage analytics requiring consent. The application is built with Electron (version 0.5.3 was the final Tauri release). It supports multiple engines, with the default being k2-fsa/OmniVoice.
Key features
- Voice cloning and voice design - Video dubbing with timed speech - Dictation with a floating widget - Transcription and audiobook creation - Local API and MCP for agents - Reusable recipes and watch folders - Support for 646 languages
Use cases
- Creating custom voices for content creation - Dubbing videos with synchronized speech - Dictation and transcription workflows - Producing audiobooks and batch audio jobs - Integrating with coding agents via MCP or local API
Getting started
One-command install (macOS / Linux): sh curl -fsSL https://voicestudio.sh/install | sh For a specific version: curl -fsSL https://voicestudio.sh/install | sh -s -- --version X.Y.Z For building from main: curl -fsSL https://voicestudio.sh/install | sh -s -- --main Uninstall: curl -fsSL https://voicestudio.sh/install | sh -s -- --uninstall On Windows, run irm https://voicestudio.sh/install | iex in PowerShell. Alternatively, download from Releases (macOS .dmg, Windows .exe, Linux .AppImage or .deb). To run from source: bash git clone https://github.com/debpalash/VoiceStudio.git cd VoiceStudio bun install bun run setup:api bun run dev
License and pricing
VoiceStudio is open source under the AGPL-3.0 license. Model weights, tokenizers, voices, and generated outputs have separate conditions; a paid app license does not grant those rights. Clone voices only with permission. The software itself is free and open source.
Based on the project's public README and repository metadata.