# Openai Whisper

> Openai Whisper is an Agent Skill for documents published in the Bitterbot-AI/bitterbot-desktop repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Local speech-to-text with the Whisper CLI (no API key).

- Skill name: `openai-whisper`
- Category: [Documents](https://www.openparable.com/skill/documents/1)
- Source: https://github.com/Bitterbot-AI/bitterbot-desktop/blob/HEAD/skills/openai-whisper/SKILL.md
- Repository: Bitterbot-AI/bitterbot-desktop (2,424 GitHub stars when collected)

## SKILL.md

# 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.

---

Source: https://www.openparable.com/skill/documents/openai-whisper (OpenParable). Cite the canonical URL above.