Skip to main content
ClaudeWave
Skill5.2k repo starsupdated today

openai-whisper

This Claude Code skill enables local speech-to-text transcription using OpenAI's Whisper command-line tool without requiring an API key. Use it when you need to convert audio files in formats like MP3 or M4A into text or subtitle formats, with options to adjust model size for balancing transcription speed and accuracy.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/the-open-agent/openagent /tmp/openai-whisper && cp -r /tmp/openai-whisper/skills/openai-whisper ~/.claude/skills/openai-whisper
Then start a new Claude Code session; the skill loads automatically.

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.