Voicebox
by Jamie Pine
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.
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.
Related Agents
Fish Audio
Generates speech, clones voices and transcribes audio through REST and WebSocket APIs backed by open-weight models, for…
Cartesia
Delivers ultra-low-latency text-to-speech and speech-to-text through the Sonic model family, with a voice-agent framewo…
AssemblyAI
Speech recognition API with real-time and batch transcription plus audio intelligence models for summarization, topic d…
Deepgram
Speech-to-text and voice AI API with real-time streaming transcription, speaker diarization, and text-to-speech for voi…