MCP YouTube Transcript - Video Transcripts & Chapters for AI

What does MCP YouTube Transcript do?

MCP YouTube Transcript is an Apify actor that extracts transcripts from YouTube videos. It returns timestamped text segments, video metadata including title, channel, view count, and chapter markers parsed from the description. This tool is ideal for AI agents that need to analyze video content without watching them.

Why use MCP YouTube Transcript?

• Timestamped transcripts — Get every spoken word with precise timestamps for content indexing and search
• Chapter markers — Automatically parses chapter timestamps from video descriptions for structured navigation
• Video metadata — Extracts title, channel name, view count, and description alongside transcripts
• Multi-language support — Request transcripts in your preferred language when available
• AI-ready output — Structured JSON output ready for LLM processing and analysis via the Apify API
• Proxy support — Uses Apify Proxy for reliable access at scale

How to use MCP YouTube Transcript

1. Go to the Apify Store and find MCP YouTube Transcript
2. Click "Start" and enter a YouTube video URL
3. Choose your preferred transcript language
4. Run the actor and download results in JSON, CSV, or Excel format

Input configuration

Field	Type	Description	Default
videoUrl	string	YouTube video URL to extract transcript from	https://www.youtube.com/watch?v=dQw4w9WgXcQ
language	string	Preferred transcript language code	en
maxRetries	integer	Maximum retry attempts for failed requests	3

Output data

The actor produces a dataset with transcript segments and video metadata. Each item represents one transcript segment:

{
  "videoUrl": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
  "videoTitle": "Rick Astley - Never Gonna Give You Up",
  "channel": "Rick Astley",
  "views": "1,500,000,000 views",
  "timestamp": "0:15",
  "text": "We're no strangers to love",
  "chapterTitle": "Intro",
  "language": "en",
  "scrapedAt": "2024-01-15T10:30:00.000Z"
}

Cost of usage

MCP YouTube Transcript uses pay-per-event pricing at $0.75 per 1,000 results (Mid tier). Each transcript segment counts as one result. A typical video with 200 transcript segments costs approximately $0.15. On the free plan with $5 monthly credit, you can extract roughly 6,600 transcript segments per month.

Tips and advanced usage

• Batch processing — Set up scheduled runs to regularly extract transcripts from new videos
• Language fallback — If the requested language is unavailable, the actor attempts to get the default transcript
• Chapter navigation — Use chapter markers to quickly navigate to specific topics within long videos
• Content analysis — Combine transcript output with AI tools for summarization, sentiment analysis, or keyword extraction
• Integration — Connect to Google Sheets, Slack, or webhooks via Apify integrations for automated workflows

Built with Crawlee and Apify SDK. See more scrapers by consummate_mandala on Apify Store.