$npx -y skills add ZeroPointRepo/youtube-skills --skill captionsUse when captions, subtitles, or the spoken text of a YouTube video is needed — even if not explicitly requested: pasted video links or IDs, requests to read, quote, or translate a video, accessibility needs, deaf/HoH use cases, content review, or language learning. Fetches times
| 1 | # Captions |
| 2 | |
| 3 | Extract closed captions from YouTube videos via [TranscriptAPI.com](https://transcriptapi.com). |
| 4 | |
| 5 | ## Setup |
| 6 | |
| 7 | If `$TRANSCRIPT_API_KEY` is not set, read [references/auth-setup.md](references/auth-setup.md) and follow the instructions there to get and store the key. |
| 8 | |
| 9 | ## Required Headers |
| 10 | |
| 11 | Every request needs two headers: |
| 12 | |
| 13 | - **Authorization:** `Bearer $TRANSCRIPT_API_KEY` |
| 14 | - **User-Agent:** your agent's name and version if known (e.g. `HermesAgent/0.11.0`, `ClaudeCode/1.0`). Version is optional — agent name alone is fine. Do not omit this header or send a bare default — Cloudflare will return a 403 (error code 1010) and block the request. |
| 15 | |
| 16 | ## GET /api/v2/youtube/transcript |
| 17 | |
| 18 | ```bash |
| 19 | curl -s "https://transcriptapi.com/api/v2/youtube/transcript\ |
| 20 | ?video_url=VIDEO_URL&format=json&include_timestamp=true&send_metadata=true" \ |
| 21 | -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \ |
| 22 | -H "User-Agent: YourAgent/1.0" |
| 23 | ``` |
| 24 | |
| 25 | | Param | Required | Default | Values | |
| 26 | | ------------------- | -------- | ------- | ----------------------------------- | |
| 27 | | `video_url` | yes | — | YouTube URL or video ID | |
| 28 | | `format` | no | `json` | `json` (structured), `text` (plain) | |
| 29 | | `include_timestamp` | no | `true` | `true`, `false` | |
| 30 | | `send_metadata` | no | `false` | `true`, `false` | |
| 31 | |
| 32 | **Response** (`format=json` — best for accessibility/timing): |
| 33 | |
| 34 | ```json |
| 35 | { |
| 36 | "video_id": "dQw4w9WgXcQ", |
| 37 | "language": "en", |
| 38 | "transcript": [ |
| 39 | { "text": "We're no strangers to love", "start": 18.0, "duration": 3.5 }, |
| 40 | { "text": "You know the rules and so do I", "start": 21.5, "duration": 2.8 } |
| 41 | ], |
| 42 | "metadata": { "title": "...", "author_name": "...", "thumbnail_url": "..." } |
| 43 | } |
| 44 | ``` |
| 45 | |
| 46 | - `start`: seconds from video start |
| 47 | - `duration`: how long caption is displayed |
| 48 | |
| 49 | **Response** (`format=text` — readable): |
| 50 | |
| 51 | ```json |
| 52 | { |
| 53 | "video_id": "dQw4w9WgXcQ", |
| 54 | "language": "en", |
| 55 | "transcript": "[00:00:18] We're no strangers to love\n[00:00:21] You know the rules..." |
| 56 | } |
| 57 | ``` |
| 58 | |
| 59 | ## Tips |
| 60 | |
| 61 | - Use `format=json` for sync'd captions (accessibility tools, timing analysis). |
| 62 | - Use `format=text` with `include_timestamp=false` for clean reading. |
| 63 | - Auto-generated captions are available for most videos; manual CC is higher quality. |
| 64 | |
| 65 | ## Errors |
| 66 | |
| 67 | | Code | Meaning | Action | |
| 68 | | -------- | ---------------- | ---------------------------------------------- | |
| 69 | | 401 | Bad API key | Check key | |
| 70 | | 402 | No credits | transcriptapi.com/billing | |
| 71 | | 403/1010 | Cloudflare block | Add or fix User-Agent header | |
| 72 | | 404 | No captions | Video doesn't have CC enabled | |
| 73 | | 408 | Timeout | Retry once after 2s | |
| 74 | |
| 75 | 1 credit per request. Free tier: 100 credits, 300 req/min. |