Local speech-to-text
Use Whisper CLI for local speech-to-text (no API key required).
52.2KUses42Likes52Views
What this skill does
# Whisper (CLI) Use `whisper` to transcribe audio locally. Quick start - `whisper /path/audio.mp3 --model medium --output_format txt --output_dir .` - `whisper /path/audio.m4a --task translate --output_format srt` Notes - Models download to `~/.cache/whisper` on first run. - `--model` defaults to `turbo` on this install. - Use smaller models for speed, larger for accuracy.
- Clarifies goals, inputs, and success criteria
- Preserves evidence and marks uncertain boundaries
- Produces structured, editable results