baoyu-youtube-transcript

You can fetch YouTube transcripts automatically by providing a video URL or ID. The skill retrieves multi-language captions without requiring API keys and caches them for quick reuse.

Yes, YouTube video captions can be extracted with chapter segmentation and speaker labeling. This produces structured transcripts with clear chapter breaks and speaker-aware formatting for downstream agents.

Yes, it fetches and caches YouTube cover images and metadata. It uses fallbacks to InnerTube and yt-dlp to ensure robust retrieval of transcripts, images, and metadata with error handling.

Translated YouTube transcripts are retrieved by specifying translation options when providing the video URL. The skill automatically handles multi-language transcript retrieval and caches the results for fast re-formatting.

When standard retrieval fails, the skill implements robust fallbacks to InnerTube and yt-dlp to fetch transcripts, images, and metadata. This ensures continuous operation with built-in error handling.

Yes, raw transcripts and cover images are cached for fast re-formatting on subsequent runs. This caching mechanism eliminates redundant fetching and speeds up processing for downstream agents.