youtube-transcript-for-llm

Extract, clean, and chunk YouTube transcripts optimized for LLM/RAG workflows.

Package Information

Released: this month
Downloads: 0 weekly / 0 monthly
Latest Version: 1.0.0
Author: MSev

Available Nodes

Documentation generating…

YouTube Transcript for LLM icon
YouTube Transcript for LLM
Extract, clean, and chunk YouTube transcripts optimized for LLM/RAG workflows.

Documentation

YouTube Transcript & LLM Chunker

Extract, clean, and format YouTube video transcripts into token-optimized chunks for RAG pipelines, AI Agents, and LLMs (OpenAI, Claude, Llama).

Built for high reliability with built-in proxy support to bypass YouTube rate limits and anti-scraping protections.

Features

  • 🚀 Instant Extraction: Fetches full YouTube video transcripts in seconds.
  • 🧩 LLM-Ready Chunking: Automatically splits transcripts into configurable chunks for vector databases and embedding models.
  • 🛡️ Anti-Blocking Architecture: Supports Apify Residential Proxies and custom proxies (Webshare, BrightData, etc.).
  • 📊 Rich Metadata: Returns video IDs, URLs, execution status, and processing metrics.
  • ⚡ n8n & Automation Friendly: Designed for seamless integration with n8n, Make, and custom REST API endpoints.

Input Parameters

Parameter Type Required Default Description
videoUrl String Yes — YouTube Video URL or Video ID (e.g., https://www.youtube.com/watch?v=...)
chunkSize Integer No 500 Target chunk size in characters/tokens for LLM processing
proxyUrl String No — Custom proxy URL (e.g., http://user:pass@host:port). Encrypted at rest.
proxyConfiguration Object No RESIDENTIAL Apify proxy configuration object

Sample Input JSON

{
  "videoUrl": "[https://www.youtube.com/watch?v=JTSiz0W8E_o](https://www.youtube.com/watch?v=JTSiz0W8E_o)",
  "chunkSize": 500,
  "proxyConfiguration": {
    "useApifyProxy": true,
    "apifyProxyGroups": ["RESIDENTIAL"]
  }
}

Discussion