SKILL.md
readonly

openai-whisper

Author：openclaw
Category：
Development
323.6k
62.4k
GitHub
name: openai-whisper
description: Local speech-to-text with the Whisper CLI (no API key).
homepage: https://openai.com/research/whisper

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.

Actions

install --global skills.sh
npx skills add openclaw/openclaw/skills/openai-whisper

Usage Guide

  1. 1. Run Install Command

    Copy the installation command above and run it in your terminal to install globally.

  2. 2. Configure Environment

    Add the required environment variables to your MCP client according to the skill description.

  3. 3. Use in Client

    Configure and enable this skill in any MCP-compatible app (e.g. Claude or Cursor).