Whisper Transcription

Wraps OpenAI's Whisper model for local audio and video transcription with a Python CLI. You get single file transcription, batch processing, and multiple output formats including SRT and VTT for subtitles. The model selection guide is actually helpful: tiny through large with clear tradeoffs between speed and accuracy. Most useful for content teams turning podcasts into blog posts or generating YouTube captions without sending files to third party APIs. Requires ffmpeg and some Python setup, but once running it's straightforward batch work. The 10x speedup with GPU is real if you're processing hours of content regularly.

skills.sh installs: 980
GitHub stars: 150
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add guia-matthieu/clawfu-skills --skill whisper-transcription --agent claude-code

Installs into .claude/skills of the current project.

Files

Whisper Transcription

Transcribe any audio or video to text using OpenAI's Whisper model - the same technology powering ChatGPT voice features.

When to Use This Skill

Podcast repurposing - Convert episodes to blog posts, show notes, social snippets
Video subtitles - Generate SRT/VTT files for YouTube, social media
Interview extraction - Pull quotes and insights from recorded calls
Content audit - Make audio/video libraries searchable
Translation - Transcribe and translate foreign language content

What Claude Does vs What You Decide

Claude Does	You Decide
Structures production workflow	Final creative direction
Suggests technical approaches	Equipment and tool choices
Creates templates and checklists	Quality standards
Identifies best practices	Brand/voice decisions
Generates script outlines	Final script approval

Dependencies

pip install openai-whisper torch ffmpeg-python click
# Also requires ffmpeg installed on system
# macOS: brew install ffmpeg
# Ubuntu: sudo apt install ffmpeg