技能创建器
skill-creator
创建、改进和评估自定义技能,把专业流程转化为可重复使用的 AI 能力。
youtube-data【数据与研究】Access YouTube video data — transcripts, metadata, channel info, search, and playlists. A lightweight alternative to Google's YouTube Data API with no quota limits. Use when the user needs structured data from YouTube videos, channels, or playlists without dealing with Google API setup, OAuth, or daily quotas.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
YouTube data access via TranscriptAPI.com — lightweight alternative to Google's YouTube Data API.
If $TRANSCRIPT_API_KEY is not set, help the user create an account (100 free credits, no card):
Step 1 — Register: Ask user for their email, generate a secure password.
node ./scripts/tapi-auth.js register --email USER_EMAIL --password SECURE_PASS --json
→ OTP sent to email. Ask user: "Check your email for a 6-digit verification code." ⚠️ SAVE THE PASSWORD — you need it again in Step 2!
Step 2 — Verify: Once user provides the OTP (use SAME password from Step 1):
node ./scripts/tapi-auth.js verify --email USER_EMAIL --password SECURE_PASS --otp CODE --json
→ Returns api_key (starts with sk_).
Step 3 — Save: Store the key (auto-configures agent + shell):
node ./scripts/tapi-auth.js save-key --key API_KEY --json
→ Ready to use. Agent runtime picks up the key automatically.
Manual option: transcriptapi.com/signup → Dashboard → API Keys.
curl -s "https://transcriptapi.com/api/v2/youtube/transcript\
?video_url=VIDEO_URL&format=json&include_timestamp=true&send_metadata=true" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY"
Response:
{
"video_id": "dQw4w9WgXcQ",
"language": "en",
"transcript": [
{ "text": "We're no strangers to love", "start": 18.0, "duration": 3.5 }
],
"metadata": {
"title": "Rick Astley - Never Gonna Give You Up",
"author_name": "Rick Astley",
"author_url": "https://www.youtube.com/@RickAstley",
"thumbnail_url": "https://i.ytimg.com/vi/dQw4w9WgXcQ/maxresdefault.jpg"
}
}
curl -s "https://transcriptapi.com/api/v2/youtube/search?q=QUERY&type=video&limit=20" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY"
Video result fields: videoId, title, channelId, channelTitle, channelHandle, channelVerified, lengthText, viewCountText, publishedTimeText, hasCaptions, thumbnails
Channel result fields (type=channel): channelId, title, handle, url, description, subscriberCount, verified, rssUrl, thumbnails
Resolve handle to ID (free):
curl -s "https://transcriptapi.com/api/v2/youtube/channel/resolve?input=@mkbhd" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY"
Returns: {"channel_id": "UCBcRF18a7Qf58cCRy5xuWwQ", "resolved_from": "@mkbhd"}
Latest 15 videos with exact stats (free):
curl -s "https://transcriptapi.com/api/v2/youtube/channel/latest?channel_id=UC_ID" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY"
Returns: channel info, results array with videoId, title, published (ISO), viewCount (exact number), description, thumbnail
All channel videos (paginated, 1 credit/page):
curl -s "https://transcriptapi.com/api/v2/youtube/channel/videos?channel_id=UC_ID" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY"
Returns 100 videos per page + continuation_token for pagination.
Search within channel (1 credit):
curl -s "https://transcriptapi.com/api/v2/youtube/channel/search\
?channel_id=UC_ID&q=QUERY&limit=30" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY"
curl -s "https://transcriptapi.com/api/v2/youtube/playlist/videos?playlist_id=PL_ID" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY"
Returns: results (videos), playlist_info (title, numVideos, ownerName, viewCount), continuation_token, has_more
| Endpoint | Cost | Data returned |
|---|---|---|
| transcript | 1 | Full transcript + metadata |
| search | 1 | Video/channel details |
| channel/resolve | free | Channel ID mapping |
| channel/latest | free | 15 videos + exact stats |
| channel/videos | 1/page | 100 videos per page |
| channel/search | 1 | Videos matching query |
| playlist/videos | 1/page | 100 videos per page |
| Code | Action |
|---|---|
| 402 | No credits — transcriptapi.com/billing |
| 404 | Not found |
| 408 | Timeout — retry once |
| 422 | Invalid param format |
Free tier: 100 credits, 300 req/min.