voicestudio

VoiceStudio is a local-first voice AI workspace for cloning voices, dubbing videos, dictating text, transcribing audio, and creating audiobooks. It keeps these workflows in a local environment while supporting agent-style automation through a local API and MCP.

Share on XLicense: AGPL-3.0

Overview

VoiceStudio is an open-source, fully local voice AI workspace for cloning voices, designing voices, dubbing videos, dictating text, transcribing audio, and creating audiobooks. It runs on local hardware with optional remote workers, and includes a local API and MCP support for agent workflows. The project helps people keep audio work in their own environment while using the same pipeline in 646 languages.

Key features

  • Voice cloning and custom voice design
  • Video dubbing with timed speech
  • Dictation, transcription, and audiobook creation
  • Local API and MCP support with optional remote workers

Best for

This fits people who want to handle voice workflows locally, including creators, teams, and agents that need a local voice pipeline. It is a good choice when you want cloning, dubbing, transcription, and audiobook work without depending on a remote-only service.

Upstream
debpalash/VoiceStudio
Fork on GitHub
Guo-astro/voicestudio
Upstream stars
48k
Category
AI agents and LLM tools
Language
Python
License
AGPL-3.0
Forked
2026-09-29
Sync status
In syncLast synced 2026-09-30