Process YouTube Transcripts: Apify, OpenAI & Pinecone Indexing
Automates fetching YouTube transcripts via Apify, processes/chunks them with timestamps, generates OpenAI embeddings, and indexes into Pinecone for semantic search. Integrates with Airtable for metadata management.
This n8n workflow serves as a powerful backend for indexing YouTube video transcripts into a Pinecone vector database, enabling efficient semantic search and retrieval in AI applications. It starts by pulling video records (URLs and metadata) from Airtable, then uses Apify to scrape transcripts with timestamps. The transcripts are updated back into Airtable, parsed to convert timestamps to seconds, chunked into meaningful segments enriched with video details and direct links, embedded via OpenAI
Platform
n8n
Category
Lifestyle
Price
$24.99
Creator
Bryce Yu
YouTube
Transcripts
Apify
OpenAI
Pinecone
Embeddings
Airtable
Vector Database
RAG
AI Indexing
How to import this workflow into n8n
1Purchase or download the workflow to get the n8n workflow JSON file.
2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
3Open each node marked with a credential warning and connect your own accounts and API keys.
4Run the workflow once manually to verify the data flow, then toggle it to Active.