Reimplementation · Creative

VoiceStudio

Author:

Summary

Local voice cloning, speech generation, dubbing, transcription and audiobook tools.

Description

A broader ElevenLabs alternative for local voice cloning, voice design, speech generation, video dubbing, dictation, transcription and audiobooks. Combines an Electron interface and Python backend with selectable speech engines, including OmniVoice, plus a local API, MCP, batch jobs and watch folders. Remote services are optional.

Source repository ↗Website ↗Documentation ↗

Community

Discord server ↗

Repository Mirrors

No mirrors found. Contribute a mirror link ↗

Screenshots

2 images

VoiceStudio: voice-cloning workspace with a demo voice.

Compatibility and scope

Status and compatibility are maintainer-reported. Inclusion is not an independent verification or certification.

Development status: Experimental
Compatibility: Partial (claimed)
Languages: Python, TypeScript, JavaScript, Rust
Platforms: Windows, macOS, Linux, Web
License: AGPL-3.0-only

Known limitations

ElevenLabs API, voice and project compatibility are not documented. Models require downloads; speed and memory needs vary by engine. Intel Macs need a remote backend; Windows ARM support is experimental. Model and tokenizer terms are separate from the app license; default OmniVoice weights are noncommercial, and some licensing reviews remain unresolved.