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.
数据来源:ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一:命令行安装(推荐)
推荐(无需提前安装 clawhub)
npx clawhub@latest --dir ~/.claude/skills install youtube-data或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install youtube-data⚠️ 需要 Node.js 18+,没有 Node?请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二:手动下载安装(无需 Node)
下载 ZIP,解压后将文件夹放到以下路径,重启 Agent 即可:
安装路径
~/.claude/skills/youtube-data/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: youtube-data description: 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. homepage: https://transcriptapi.com user-invocable: true metadata: {"openclaw":{"emoji":"📊","requires":{"env":["TRANSCRIPT_API_KEY"],"bins":["node"],"config":["~/.openclaw/openclaw.json"]},"primaryEnv":"TRANSCRIPT_API_KEY"}} ---
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.
node ./scripts/tapi-auth.js register --email USER_EMAIL
→ OTP sent to email. Ask user: _"Check your email for a 6-digit verification code."_
Step 2 — Verify: Once user provides the OTP:
node ./scripts/tapi-auth.js verify --token TOKEN_FROM_STEP_1 --otp CODE
> API key saved to ~/.openclaw/openclaw.json. See File Writes below for details. Existing file is backed up before modification.
Manual option: transcriptapi.com/signup → Dashboard → API Keys.
The verify and save-key commands save the API key to ~/.openclaw/openclaw.json (sets skills.entries.transcriptapi.apiKey and enabled: true). Existing file is backed up to ~/.openclaw/openclaw.json.bak before modification.
To use the API key in terminal/CLI outside the agent, add to your shell profile manually: export TRANSCRIPT_API_KEY=
Full OpenAPI spec: transcriptapi.com/openapi.json — consult this for the latest parameters and schemas.
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
Channel endpoints accept channel — an @handle, channel URL, or UC... ID. No need to resolve first.
Resolve handle to ID (free):
curl -s "https://transcriptapi.com/api/v2/youtube/channel/resolve?input=@TED" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY"
Returns: {"channel_id": "UCsT0YIqwnpJCM-mx7-gSA4Q", "resolved_from": "@TED"}
Latest 15 videos with exact stats (free):
curl -s "https://transcriptapi.com/api/v2/youtube/channel/latest?channel=@TED" \
-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=@NASA" \
-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=@TED&q=QUERY&limit=30" \
-H "Authorization: Bearer $TRANSCRIPT_API_KEY"
Accepts playlist — a YouTube playlist URL or playlist ID.
curl -s "https://transcriptapi.com/api/v2/youtube/playlist/videos?playlist=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.
安装 Youtube Data 后,可以对 AI 说这些话来触发它
Help me get started with Youtube Data
Explains what Youtube Data does, walks through the setup, and runs a quick demo based on your current project
Use Youtube Data to access YouTube video data — transcripts, metadata, channel info, se...
Invokes Youtube Data with the right parameters and returns the result directly in the conversation
What can I do with Youtube Data in my design & creative workflow?
Lists the top use cases for Youtube Data, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/youtube-data/ 目录(个人级,所有项目可用),或 .claude/skills/youtube-data/(项目级)。重启 AI 客户端后,用 /youtube-data 主动调用,或让 AI 根据上下文自动发现并使用。
Youtube Data 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
Youtube Data 可免费安装使用。请查阅仓库了解许可证信息。
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.
Youtube Data 属于「Design & Creative」分类,该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my design & creative tasks using Youtube Data
Identifies repetitive steps in your workflow and sets up Youtube Data to handle them automatically