# Openai Whisper

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

- Skill: `gabrielkoerich/openai-whisper` (Agent Skill, multi-file: 5 files)
- Install (CLI): `npx skillmds@latest add gabrielkoerich/openai-whisper`
- Raw SKILL.md: https://api.skillmd.com/api/skills/gabrielkoerich/openai-whisper/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Integrations & APIs
- Author: gabrielkoerich (https://skillmd.com/u/gabrielkoerich)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/gabrielkoerich/openai-whisper

---


# Whisper (CLI)

Use `whisper` to transcribe audio locally.

## Requirements

Install the Whisper CLI:

```bash
# macOS
brew install openai-whisper

# pip
pip install openai-whisper
```

## 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.