VoiceStudio

by debpalash

The free, local alternative to ElevenLabs: clone a voice, design one, dub a video, dictate, transcribe.

AGPL-3.0 FreeOpen sourceLocal

View on GitHub →

What it does

Voice cloning, voice design, timed video dubbing, dictation, transcription and audiobooks
646 languages claimed (French included), OmniVoice engine by default, other engines in the catalog
Everything stays on your machine; local API and MCP server for your agents

! AGPL-3.0 license: if you offer the software (or a modified version) as an online service, you must share the code. Only clone a voice with the person's consent. Windows on ARM is experimental; Intel Mac: UI only, with a remote backend. Figures and features come from the repo (not tested by PixDig).

Install it

Requirements: Linux, macOS or Windows. On first launch the app sets up its Python backend and downloads its models (several GB).

Linux / macOS: install the latest release

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

Windows (PowerShell)

irm https://voicestudio.sh/install | iex

Open VoiceStudio, pick your engine and models

~/.local/bin/VoiceStudio

The prompt for your agent

Paste it into your coding agent: it checks the requirements and installs it for you.

Claude CodeCodexCursorGemini CLIopencode

Prompt

Install VoiceStudio (https://github.com/debpalash/VoiceStudio) on my machine.
1. Check the requirements: Linux, macOS or Windows. On first launch the app sets up its Python backend and downloads its models (several GB). If anything is missing, tell me before installing anything.
2. Follow the official method:
- Linux / macOS: install the latest release: curl -fsSL https://voicestudio.sh/install | sh
- Windows (PowerShell): irm https://voicestudio.sh/install | iex
- Open VoiceStudio, pick your engine and models: ~/.local/bin/VoiceStudio
3. Check that it works, then explain how to launch it and where to start.

Always review what your agent is about to run, especially install commands.