yt-transcribe

SKILL.md

Use yt-transcribe to get the actual spoken content from YouTube videos. Web search and fetch tools cannot access video content - they only see metadata.

| -q | Required for LLMs - clean stdout, no progress noise | | -m tiny | Faster transcription (less accurate) | | -m medium | More accurate (slower, larger model) | | -o file | Save to file instead of stdout | | -f srt/vtt | Include timestamps |

Always use -q flag - suppresses progress output, gives clean transcript to stdout.

當用戶詢問 YouTube 視頻內容、想要了解視頻內容、需要來自 YouTube URL 的信息，或者視頻轉錄可以回答他們的問題時使用 來源：mhagrelius/dotfiles。

查看原文