From sundial-org-awesome-openclaw-skills-4
Transcribes YouTube videos and local audio/video files with speaker diarization via ElevenLabs. Outputs clean speaker-labeled transcripts ready for LLM analysis.
How this skill is triggered — by the user, by Claude, or both
Slash command
/sundial-org-awesome-openclaw-skills-4:transcribeeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Transcribe YouTube videos and local media files with speaker diarization via ElevenLabs.
Transcribe YouTube videos and local media files with speaker diarization via ElevenLabs.
# YouTube video
transcribee "https://www.youtube.com/watch?v=..."
# Local video
transcribee ~/path/to/video.mp4
# Local audio
transcribee ~/path/to/podcast.mp3
Always quote URLs containing & or special characters.
Transcripts save to: ~/Documents/transcripts/{category}/{title}-{date}/
| File | Use |
|---|---|
transcription.txt | Speaker-labeled transcript |
transcription-raw.txt | Plain text, no speakers |
transcription-raw.json | Word-level timings |
metadata.json | Video info, language, category |
brew install yt-dlp ffmpeg
| Error | Fix |
|---|---|
yt-dlp not found | brew install yt-dlp |
ffmpeg not found | brew install ffmpeg |
| API errors | Check .env file in transcribee directory |
npx claudepluginhub sundial-org/awesome-openclaw-skillsTranscribes YouTube/podcast/audio URLs to clean text using auto-captions or local whisper-cpp with Silero VAD. Provides verbatim transcripts as source-of-truth artifacts for research and quote extraction.
Transcribes audio files using ElevenLabs Scribe v2 with support for 90+ languages, speaker diarization, and word-level timestamps.
Transcribes audio/video from YouTube URLs or local files to structured markdown with timestamps, speaker labels, and chapters using Google Gemini API.