Runs a local voice studio for voice cloning, text-to-speech and Whisper dictation, and lets agents speak or transcribe through a built-in MCP server and REST API.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with Voicebox connected:
- Voice Cloning
Use Voicebox to clone a voice from a few seconds of audio: ‹what you need›
- Whisper Transcription
Use Voicebox to transcribe audio: ‹what you need›
- Global Dictation
Use Voicebox to dictate into any text field: ‹what you need›
Connect it over MCP
Connect Voicebox as an MCP server, following its setup instructions at https://github.com/jamiepine/voicebox
Its page: github.com/jamiepine/voicebox
Call the API
Auth None needed
Its page: github.com/jamiepine/voicebox
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- MCPAPI
- Auth
- None
- Skills
- 4
Skills
Agent Voice Output
Lets any MCP-aware agent speak in a cloned voice via the voicebox_speak tool or POST /speak, with a per-agent voice binding.
Voice Cloning
Clones a voice from a few seconds of audio and generates speech in 23 languages across seven TTS engines, with multi-sample profiles.
Whisper Transcription
Transcribes audio with OpenAI Whisper on MLX or PyTorch, exposed through the /transcribe endpoint and the voicebox_transcribe MCP tool.
Global Dictation
Dictates into any text field with a push-to-talk or toggle hotkey, pasting the transcript into the focused field on macOS.