baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面", "视频封面", "video thumbnail", "video cover image", or provides a YouTube URL and wants the transcript/subtitle text or cover image extracted.
Security Assessment
About baoyu-youtube-transcript
The baoyu-youtube-transcript skill is designed to facilitate the downloading of transcripts and subtitles from YouTube videos, addressing the need for users to easily access video content in text format. By providing a straightforward method to extract subtitles and cover images using either a URL or video ID, this skill eliminates the need for complex setups or API keys. It directly utilizes YouTube's InnerTube API and seamlessly falls back to `yt-dlp` when necessary, ensuring a reliable experience for users seeking transcripts.
FAQ
How do I use the baoyu-youtube-transcript skill?
You can use the skill by running the command with a YouTube URL or video ID, along with optional parameters for language, format, and other features.
What formats can I download the transcripts in?
Transcripts can be downloaded in text or SRT format.
Is there a requirement for an API key?
No, this skill does not require an API key as it uses YouTube's InnerTube API directly.
Can I specify multiple languages for the transcripts?
Yes, you can specify multiple language codes in priority order.
What should I do if I encounter issues with downloading?
You can use the --refresh option to force a re-fetch of the data, ignoring any cached information.
Install baoyu-youtube-transcript
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
jimliu/baoyu-skills