Summarize YouTube transcripts in any language with Google Gemini & Google Docs
Needs changesWhat this workflow does
This AI workflow has 8 nodes and runs when someone submits an n8n form (“summarize youtube videos from transcript for social media”). Along the way it connects Google Gemini Chat Model and Google Docs. It also calls youtube-transcriptor-pro.p.rapidapi.com over HTTP.
How it runs
Trigger: When someone submits an n8n form (“summarize youtube videos from transcript for social media”).
- Mapper (Edit Fields (Set)): sets 2 fields: videoUrl, language
- YouTube Transcript AI (HTTP Request): calls youtube-transcriptor-pro.p.rapidapi.com (POST)
- Formator (Code): runs custom JavaScript code
- AI Agent: runs an AI agent, with model: Google Gemini Chat Model
- Optimizer (Code): runs custom JavaScript code
- Google Docs: update
Services it uses
HTTP calls to: youtube-transcriptor-pro.p.rapidapi.com
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in AI Agent1 (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent1 (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (7)
- n8n Form Trigger
n8n-nodes-base.formTrigger - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Google Docs
n8n-nodes-base.googleDocs - Edit Fields (Set)
n8n-nodes-base.set - Code
n8n-nodes-base.code - AI Agent
@n8n/n8n-nodes-langchain.agent - HTTP Request
n8n-nodes-base.httpRequest
From the author
YouTube Transcript Summarization in Any Language for Social Media This n8n workflow automates the process of: 1. Retrieving YouTube Video Transcripts: It fetches the transcript for any YouTube video URL provided using the YouTube Transcript API from RapidAPI.…