Transcribe YouTube videos & create GEO summaries with Whisper and GPT-4o-mini in Notion

by Rahul Joshi ✓ · 2,580 views · created 2025-11-21 · Document Extraction, AI Summarization

What this workflow does

This AI workflow has 14 nodes and runs on a schedule (every hour). Along the way it connects Notion, YouTube, OpenAI and OpenAI Chat Model.

How it runs

Trigger: On a schedule (every hour).

1. YouTube: get (video)
2. Set - Prepare Video Metadata (Edit Fields (Set)): sets 6 fields: videoId, title, description…
3. Merge: merges the data from its input branches
4. HTTP - Get YouTube Audio (HTTP Request): calls an HTTP API
5. AI Agent: runs an AI agent, with model: OpenAI Chat Model; memory: Memory - Conversation Buffer; output parser: Output Parser - Structured JSON
6. HTTP - Download Audio File (HTTP Request): calls an HTTP API
7. Function - Parse GEO JSON (Code): runs custom JavaScript code
8. OpenAI: transcribe (audio)
9. Notion: work with database page
10. If: checks a condition and branches into true / false

Services it uses

NotionYouTubeOpenAIOpenAI Chat Model

Before you upgrade to n8n 3.0

Nodes used (13)

• Schedule Triggern8n-nodes-base.scheduleTrigger
• Edit Fields (Set)n8n-nodes-base.set
• HTTP Requestn8n-nodes-base.httpRequest
• Ifn8n-nodes-base.if
• Mergen8n-nodes-base.merge
• Coden8n-nodes-base.code
• Notionn8n-nodes-base.notion
• YouTuben8n-nodes-base.youTube
• OpenAI@n8n/n8n-nodes-langchain.openAi
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi
• Simple Memory@n8n/n8n-nodes-langchain.memoryBufferWindow
• Structured Output Parser@n8n/n8n-nodes-langchain.outputParserStructured
• AI Agent@n8n/n8n-nodes-langchain.agent

From the author

📊 Description Automate your YouTube research workflow by extracting audio from any video, transcribing it with Whisper AI, and generating structured GEO (Goal–Execution–Outcome) summaries using GPT-4o-mini. 🎥🤖 This template transforms unstructured video…

View the original on n8n.io → Check your own copy