Download
yovoice is an open-source, local-first AI audio and music production studio for Windows, macOS, and Linux. It generates natural speech, cloned voices, songs, instrumental tracks, and musical scores without requiring cloud processing. Users can create voices from text descriptions or clone reference voices while adjusting emotional delivery and speaking style. Its dubbing tools convert scripts and subtitles into character-specific dialogue. Music generation supports written lyrics, style prompts, instrumental compositions, and sound effects through multiple AI models. The integrated workstation provides waveform editing, take comparisons, and multitrack arrangement tools. MIDI composition and General MIDI rendering enable structured music production and export. Optional AI assistant and MCP integrations automate creative tasks while local processing keeps source materials on the user's device.
Features
- Offline text-to-speech synthesis with expressive voices and emotional delivery controls
- Zero-shot voice cloning and custom voice design from descriptions or reference audio
- AI song generation with custom lyrics, musical styles, and synchronized playback
- Multitrack music composition with MIDI import, General MIDI rendering, and stem export
- Character-based story dubbing with subtitle import and line-by-line speech generation
- Waveform editing, take versioning, and optional AI assistant integration through MCP
Project Samples
