AgentSkillsCN

transcribee

对 YouTube 视频以及本地音频/视频文件进行转录,并支持说话人分离。当用户要求转录 YouTube URL、播客、视频或音频文件时,此功能便能派上用场。输出清晰标注说话人的转录文本,可直接用于 LLM 分析。

SKILL.md
--- frontmatter
name: transcribee
description: Transcribe YouTube videos and local audio/video files with speaker diarization. Use when user asks to transcribe a YouTube URL, podcast, video, or audio file. Outputs clean speaker-labeled transcripts ready for LLM analysis.

Transcribee

Transcribe YouTube videos and local media files with speaker diarization via ElevenLabs.

Usage

bash
# 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.

Output

Transcripts save to: ~/Documents/transcripts/{category}/{title}-{date}/

FileUse
transcription.txtSpeaker-labeled transcript
transcription-raw.txtPlain text, no speakers
transcription-raw.jsonWord-level timings
metadata.jsonVideo info, language, category

Supported Formats

  • Audio: mp3, m4a, wav, ogg, flac
  • Video: mp4, mkv, webm, mov, avi
  • URLs: youtube.com, youtu.be

Dependencies

bash
brew install yt-dlp ffmpeg

Troubleshooting

ErrorFix
yt-dlp not foundbrew install yt-dlp
ffmpeg not foundbrew install ffmpeg
API errorsCheck .env file in transcribee directory