# Openai Whisper

> Transcribe audio locally with the Whisper CLI. No API key needed.

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

---


# Whisper CLI

Transcribe audio locally using OpenAI Whisper.

## Quick start

```bash
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.
- Default model is `turbo`.
- Use smaller models for speed, larger for accuracy.