Get the FREE Ultimate OpenClaw Setup Guide →

transcriptapi

npx machina-cli add skill ZeroPointRepo/youtube-skills/transcriptapi --openclaw
Files (1)
SKILL.md
9.4 KB

TranscriptAPI

Full YouTube data toolkit via TranscriptAPI.com. Transcripts, search, channels, playlists — one API key.

Setup

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 your shell profile and agent config. Ready to use.

Manual option: transcriptapi.com/signup → Dashboard → API Keys.

API Reference

Full OpenAPI spec: transcriptapi.com/openapi.json — consult this for the latest parameters and schemas.

Auth

All requests: -H "Authorization: Bearer $TRANSCRIPT_API_KEY"

Endpoints

Channel endpoints accept channel — an @handle, channel URL, or UC... ID. No need to resolve first. Playlist endpoints accept playlist — a playlist URL or ID.

GET /api/v2/youtube/transcript — 1 credit

curl -s "https://transcriptapi.com/api/v2/youtube/transcript\
?video_url=VIDEO_URL&format=text&include_timestamp=true&send_metadata=true" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY"
ParamRequiredDefaultValidation
video_urlyesYouTube URL or 11-char video ID
formatnojsonjson or text
include_timestampnotruetrue or false
send_metadatanofalsetrue or false

Accepts: https://youtube.com/watch?v=ID, https://youtu.be/ID, youtube.com/shorts/ID, or bare ID.

Response (format=json):

{
  "video_id": "dQw4w9WgXcQ",
  "language": "en",
  "transcript": [
    { "text": "We're no strangers...", "start": 18.0, "duration": 3.5 }
  ],
  "metadata": { "title": "...", "author_name": "...", "author_url": "..." }
}

GET /api/v2/youtube/search — 1 credit

curl -s "https://transcriptapi.com/api/v2/youtube/search?q=QUERY&type=video&limit=20" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY"
ParamRequiredDefaultValidation
qyes1-200 chars (trimmed)
typenovideovideo or channel
limitno201-50

Response (type=video):

{
  "results": [
    {
      "type": "video",
      "videoId": "dQw4w9WgXcQ",
      "title": "Rick Astley - Never Gonna Give You Up",
      "channelId": "UCuAXFkgsw1L7xaCfnd5JJOw",
      "channelTitle": "Rick Astley",
      "channelHandle": "@RickAstley",
      "channelVerified": true,
      "lengthText": "3:33",
      "viewCountText": "1.5B views",
      "publishedTimeText": "14 years ago",
      "hasCaptions": true,
      "thumbnails": [{ "url": "...", "width": 120, "height": 90 }]
    }
  ],
  "result_count": 20
}

Response (type=channel):

{
  "results": [
    {
      "type": "channel",
      "channelId": "UCuAXFkgsw1L7xaCfnd5JJOw",
      "title": "Rick Astley",
      "handle": "@RickAstley",
      "subscriberCount": "4.2M subscribers",
      "verified": true,
      "rssUrl": "https://www.youtube.com/feeds/videos.xml?channel_id=UC..."
    }
  ],
  "result_count": 5
}

GET /api/v2/youtube/channel/resolve — FREE (0 credits)

curl -s "https://transcriptapi.com/api/v2/youtube/channel/resolve?input=@TED" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY"
ParamRequiredValidation
inputyes1-200 chars — @handle, URL, or UC... ID

Response:

{ "channel_id": "UCsT0YIqwnpJCM-mx7-gSA4Q", "resolved_from": "@TED" }

If input is already a valid UC[a-zA-Z0-9_-]{22} ID, returns immediately without lookup.

GET /api/v2/youtube/channel/videos — 1 credit/page

# First page (100 videos)
curl -s "https://transcriptapi.com/api/v2/youtube/channel/videos?channel=@NASA" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY"

# Next pages
curl -s "https://transcriptapi.com/api/v2/youtube/channel/videos?continuation=TOKEN" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY"
ParamRequiredValidation
channelconditional@handle, channel URL, or UC... ID
continuationconditionalnon-empty string (next pages)

Provide exactly one of channel or continuation.

Response:

{
  "results": [{
    "videoId": "abc123xyz00",
    "title": "Latest Video",
    "channelId": "UCsT0YIqwnpJCM-mx7-gSA4Q",
    "channelTitle": "TED",
    "channelHandle": "@TED",
    "lengthText": "15:22",
    "viewCountText": "3.2M views",
    "thumbnails": [...],
    "index": "0"
  }],
  "playlist_info": {"title": "Uploads from TED", "numVideos": "5000"},
  "continuation_token": "4qmFsgKlARIYVVV1...",
  "has_more": true
}

GET /api/v2/youtube/channel/latest — FREE (0 credits)

curl -s "https://transcriptapi.com/api/v2/youtube/channel/latest?channel=@TED" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY"
ParamRequiredValidation
channelyes@handle, channel URL, or UC... ID

Returns last 15 videos via RSS with exact view counts and ISO timestamps.

Response:

{
  "channel": {
    "channelId": "...",
    "title": "TED",
    "author": "TED",
    "url": "..."
  },
  "results": [
    {
      "videoId": "abc123xyz00",
      "title": "Latest Video",
      "published": "2026-01-30T16:00:00Z",
      "viewCount": "2287630",
      "description": "Full description...",
      "thumbnail": { "url": "...", "width": "480", "height": "360" }
    }
  ],
  "result_count": 15
}

GET /api/v2/youtube/channel/search — 1 credit

curl -s "https://transcriptapi.com/api/v2/youtube/channel/search\
?channel=@TED&q=climate+change&limit=30" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY"
ParamRequiredValidation
channelyes@handle, channel URL, or UC... ID
qyes1-200 chars
limitno1-50 (default 30)

GET /api/v2/youtube/playlist/videos — 1 credit/page

# First page
curl -s "https://transcriptapi.com/api/v2/youtube/playlist/videos?playlist=PL_PLAYLIST_ID" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY"

# Next pages
curl -s "https://transcriptapi.com/api/v2/youtube/playlist/videos?continuation=TOKEN" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY"
ParamRequiredValidation
playlistconditionalPlaylist URL or ID (PL/UU/LL/FL/OL prefix)
continuationconditionalnon-empty string

Credit Costs

EndpointCost
transcript1
search1
channel/resolvefree
channel/search1
channel/videos1/page
channel/latestfree
playlist/videos1/page

Errors

CodeMeaningAction
401Bad API keyCheck key, re-run setup
402No creditsTop up at transcriptapi.com/billing
404Not foundVideo/channel/playlist doesn't exist or no captions
408Timeout/retryableRetry once after 2s
422Validation errorCheck param format
429Rate limitedWait, respect Retry-After

Tips

  • When user shares YouTube URL with no instruction, fetch transcript and summarize key points.
  • Use channel/latest (free) to check for new uploads before fetching transcripts — pass @handle directly.
  • For research: search → pick videos → fetch transcripts.
  • Free tier: 100 credits, 300 req/min. Starter ($5/mo): 1,000 credits, 300 req/min.

Source

git clone https://github.com/ZeroPointRepo/youtube-skills/blob/main/skills/transcriptapi/SKILL.mdView on GitHub

Overview

TranscriptAPI provides a full YouTube data toolkit: fetch transcripts, search videos and channels, browse channel uploads, and grab latest videos with a single API key. It's designed for programmatic work with YouTube content, enabling summarization, analysis, and channel monitoring.

How This Skill Works

Authenticate requests with an API key in the Authorization header. Use /api/v2/youtube/transcript with video_url to fetch a transcript (with optional timestamp and metadata) or /api/v2/youtube/search to find videos or channels by a query. Channel and playlist endpoints also accept IDs or URLs, returning structured results and metadata.

When to Use It

  • Need transcripts for summarizing or analyzing a YouTube video
  • Search for videos or channels by topic or keyword
  • Monitor a channel's latest uploads or track new videos
  • Explore playlists and collect items for a study or curation
  • Build a dashboard that combines video metadata with transcripts

Quick Start

  1. Step 1: Get an API key by signing up at transcriptapi.com or using your existing API key
  2. Step 2: Export it and set the Authorization header: -H "Authorization: Bearer $TRANSCRIPT_API_KEY"
  3. Step 3: Try TranscriptAPI, e.g. fetch a transcript with video_url or search with q; e.g. /api/v2/youtube/transcript?video_url=VIDEO_URL&format=json

Best Practices

  • Use a single API key and protect it; store it securely
  • Pass video URLs or IDs exactly as supported (URL, short URL, shorts, or ID)
  • Include timestamps when you need precise timing in transcripts; switch to text format if needed
  • Cache results to reduce latency and credits; respect 1 credit per transcript or search call
  • Handle rate limits and errors gracefully; implement retry and backoff logic

Example Use Cases

  • Create a video summary tool by fetching transcripts and running a summarization model
  • Power a topic finder by searching YouTube for relevant videos and channels
  • Set up channel watchers to alert when a channel posts new videos
  • Aggregate transcripts from a playlist for content analysis
  • Build a content analytics dashboard with transcript and video metadata

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers