Menu
Transcribe audio locally with the Whisper CLI. No API key needed.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Create a new skill or improve an existing one. Use when the user wants to capture a workflow as a reusable skill, edit a skill, or optimize its triggering.
Create Scratch 3.0 projects using Python and ScratchGen. Use when the user wants to generate a .sb3 file with sprites, scripts, and assets.
Search across multiple web providers with automatic failover. Use when the user needs quota-aware, multi-provider web search.
Create an audio interview with a selected agent using OpenAI TTS. Generates a single MP3 file with a Q&A podcast session.
Write technical blog posts about real engineering challenges. Use when the user wants technical content, blog posts, tutorials, or explanations for mixed audiences including non-technical readers.
Automate browser interactions for scraping, testing, and workflows. Use when the user wants to navigate pages, fill forms, extract data, or take screenshots with Puppeteer or Playwright.
| name | openai-whisper |
| description | Transcribe audio locally with the Whisper CLI. No API key needed. |
| license | MIT |
| compatibility | claude-code opencode github-copilot devin pi cursor |
Transcribe audio locally using OpenAI Whisper.
whisper /path/audio.mp3 --model medium --output_format txt --output_dir .
whisper /path/audio.m4a --task translate --output_format srt
~/.cache/whisper on first run.turbo.