Local Whisper STT Local speech-to-text using OpenAI's Whisper. Fully offline after initial model download. Usage Models | Model | Size | Notes | |-------|------|-------| | | 39M | Fastest | | | 74M | Default | | | 244M | Good balance | | | 809M | Best speed/quality | | | 1.5GB | Maximum accuracy | Options - — Model size (default: base) - — Language code (auto-detect if omitted) - — Include word timestamps - — JSON output - — Suppress progress Setup Uses uv-managed venv at . To reinstall: ---