The open-source AI voice studio. Clone, dictate, create.
Voicebox is a local AI voice studio that clones voices, generates speech, and turns spoken input into text on a computer. People use it for dictation, voice creation, and giving MCP-compatible agents spoken output. The catalogue add-ons support workflows around operating Voicebox.
Latest release v0.5.0 · 25 Apr 2026
4 files for Claude Code and Codex: add-tts-engine, draft-release-notes, release-bump, triage-prs .
.agents/skills/add-tts-engine/SKILL.md A 56 tok .agents/skills/draft-release-notes/SKILL.md A 56 tok .agents/skills/release-bump/SKILL.md A 54 tok .agents/skills/triage-prs/SKILL.md A 80 tok These files are jamiepine/voicebox's own configuration — they tell Claude Code and Codex how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.