100% private on-device speech-to-text and meeting transcription with local AI models on macOS
Universal speech-to-text inference library supporting 16+ model families with GPU acceleration
Open-source ElevenLabs alternative for voice cloning, video dubbing, and TTS - all running locally
Build local voice agents with open-source AI models
Frontier CoreML audio models for iOS/macOS — local speech-to-text, TTS, VAD, and speaker diarization
Local AI subtitle generation for video editors—no cloud, no subscription.
Local-first dictation & meeting transcription for macOS with on-device AI
Free, open-source AI dictation for Mac with context awareness
