captions
Fetch closed captions and transcripts from YouTube videos with precise timing information. Choose between structured JSON for sync'd playback and accessibility tools, or plain text for easy reading. Supports both manual captions and auto-generated transcripts.
Captions extracts timestamped transcripts and closed captions from any YouTube video via TranscriptAPI.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-05-20
Captions extracts timestamped transcripts and closed captions from any YouTube video via TranscriptAPI. Fetch closed captions and transcripts from YouTube videos with precise timing information. Choose between structured JSON for sync'd playback and accessibility tools, or plain text for easy reading. Supports both manual captions and auto-generated transcripts.
Use it when
- Yes.
- captions supports two output formats: structured JSON for synchronized playback and accessibility integration.
Verify before relying
Read SKILL.md below before installing (2 files). Open directory: indexed for reading, not audited.
Install
ZeroPointRepo/youtube-skills/captions
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I get YouTube video captions using captions?
captions lets you fetch closed captions and transcripts from YouTube videos with precise timing information. You can retrieve structured JSON data for synced playback and accessibility tools, or plain text for easy reading. The skill supports both manually created captions and auto-generated transcripts.
Can captions extract subtitles from YouTube with timestamps?
Yes. captions is designed to fetch video captions with timestamps, giving you timestamped data that preserves the exact timing of each caption segment. This makes it ideal for accessibility needs, closed captioning workflows, and synced playback in custom applications.
What formats does captions support for transcript output?
captions supports two output formats: structured JSON for synchronized playback and accessibility integration, and plain text for straightforward reading and quoting. Both formats preserve caption content; JSON includes timing data while plain text prioritizes readability.
Can I use captions for language learning from video dialogue?
Yes. captions retrieves and analyzes spoken text from videos, making it useful for language learning by letting you read and quote video dialogue. You can access transcripts to study pronunciation, vocabulary, and phrasing in context.
Does captions work with auto-generated transcripts or only manual captions?
captions supports both manually created captions and auto-generated transcripts from YouTube. This flexibility ensures you can extract caption data regardless of whether the video creator provided hand-written captions or YouTube generated them automatically.
How can I integrate captions into my application via API?
captions provides API integration for fetching video metadata and caption data programmatically. You can retrieve timestamped transcripts and structured caption information to build accessibility features, translation tools, or custom video players into your application.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Captions
Extract closed captions from YouTube videos via
(truncated - see the full file via the links below)
File tree — 2 files
clawhub/captions/SKILL.md
clawhub/captions/references/auth-setup.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Extract timestamped captions and transcripts from YouTube videos”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Subtitles retrieves timestamped transcripts from YouTube videos in both structured and plain-text formats. Use it to extract spoken content, support language learning, enable accessibility, or prepare text for translation. Requires a free TranscriptAPI key.
Fetch complete transcripts from YouTube videos by pasting a link or video ID. The skill handles multiple URL formats, returns text with timestamps, and includes video metadata like title and author. Use it for summarizing, quoting, translating, or fact-checking video content.
Turn YouTube videos into readable text instantly. Paste a link or video ID to retrieve transcripts with optional timestamps and video metadata like title and channel. Supports standard YouTube URLs, shortened links, and Shorts.
YouTube Full gives agents direct access to video transcripts, captions, and metadata through TranscriptAPI. Search videos and channels, browse playlists, fetch latest uploads, and pull full transcripts with timestamps—all via simple API calls that work from any environment.
YouTube Data retrieves transcripts, video metadata, search results, channel upload history, and playlist contents through TranscriptAPI, bypassing Google API rate limits and authentication overhead. Access video details, channel information, and structured YouTube content with simple API calls and a free tier of 100 credits.
yt connects your agent to YouTube content through TranscriptAPI, letting you pull transcripts from videos, search for specific content, and fetch the latest uploads from any channel using just an API key. Works with video links, channel handles, or direct IDs.
More skills youtube-api (MIT) · youtube-search (MIT) · youtube-playlist (MIT)