Skill1.3k repo starsupdated today

openai-whisper

This Claude Code skill provides local speech-to-text transcription using OpenAI's Whisper command-line tool without requiring API authentication. Use it to transcribe audio files in formats like MP3 and M4A directly on your system, with options to adjust model size for speed versus accuracy trade-offs and output formats including plain text and subtitles.

View source Repository: trpc-agent-go

Install in Claude Code

Copy

git clone --depth 1 https://github.com/trpc-group/trpc-agent-go /tmp/openai-whisper && cp -r /tmp/openai-whisper/openclaw/skills/openai-whisper ~/.claude/skills/openai-whisper

Then start a new Claude Code session; the skill loads automatically.

Definition

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.