# Openai Whisper

> Local speech-to-text with the Whisper CLI (no API key); Don't use if you need cloud transcription with no local model; prefer openai-whisper-api.

- Skill: `unisone/openai-whisper` (Agent Skill)
- Install (CLI): `npx skillmds@latest add unisone/openai-whisper`
- Raw SKILL.md: https://api.skillmd.com/api/skills/unisone/openai-whisper/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: unisone (https://skillmd.com/u/unisone)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/unisone/openai-whisper

---


# Whisper (CLI)

Use `whisper` to transcribe audio locally.

## Routing

- ❌ Don't use if you need cloud transcription (no local model / no local compute).
- ✅ Prefer `openai-whisper-api` for cloud transcription.

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.