Private voice-to-text dictation, meeting transcription, notes, and AI-assisted cleanup.
OpenVoice V2 local voice cloning with MeloTTS base speakers, Fobia asset hydration, and app-scoped checkpoint/cache paths.
Gradio browser UI for local Whisper/faster-whisper transcription, subtitles, translation, VAD, diarization, and audio preprocessing.
Local-first AI voice studio for voice cloning, TTS, STT, dictation, effects, stories, REST API, and MCP voice tools.
