Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Downloads Instagram Reels, extracts the audio, and transcribes it using Groq Whisper. Returns a full transcript with timestamps alongside the original caption, uploader name, and video duration. Also works with TikTok, YouTube Shorts, and other platforms yt-dlp supports.
Groq Whisper returns transcripts in 1-2 seconds for free, with no file upload UI or screen recording needed, just a URL.
When to use it
- Transcribing spoken instructions from cooking or tutorial reels
- Pulling exact quotes from interview clips posted as reels
- Archiving captions and audio content from public accounts before deletion
- Converting fitness video narration to searchable text
- Getting a transcript of a TikTok or Short without screen recording
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: 'Transcribe this reel: https://www.instagram.com/reel/ABC123/'
- 1Run yt-dlp to extract metadata and locate the m4a audio CDN URL
- 2Download the m4a audio file directly from the CDN
- 3Convert m4a to mp3 using ffmpeg
- 4Send the mp3 to Groq Whisper API and retrieve the transcript with timestamps
- 5Extract caption, author, and duration from the metadata JSON
Full spoken transcript with timestamps, original reel caption, author name, and video duration in seconds
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.