🎬 Summarize YouTube videos and generate thumbnails using AI Agent and deAPI
⚡ 151 views · 🎬 Content Creation & Video
💡 Pro Tip — YouTube’s API quotas can be a bottleneck when you’re pulling data at scale. ScraperNode is a community node with dedicated scrapers for channels, videos, and comments — no quota limits, just structured data.
Description
Who is this for?
- YouTube creators who want to speed up their post-production workflow
- Content repurposers who turn videos into written summaries
- Social media managers handling multiple YouTube channels
- Anyone who needs quick, AI-generated thumbnails from video content
What problem does this solve?
Watching a full video to write a summary and then designing a matching thumbnail is tedious. This workflow does both automatically — transcribe, summarize, and generate a professional 1280x720 thumbnail — all from a single YouTube URL.
What this workflow does
- Takes a YouTube video URL as input
- Transcribes the full video using deAPI (Whisper Large V3)
- AI Agent analyzes the transcript, writes a concise summary, and uses the deAPI Prompt Booster tool to craft an optimized thumbnail image prompt
- Generates a 1280x720 landscape thumbnail using deAPI
- Uploads the thumbnail to Google Drive
Setup
Requirements
- n8n instance (self-hosted or n8n Cloud)
- deAPI account for video transcription, prompt boosting, and image generation
- Anthropic account for the AI Agent
- Google Drive API access for file uploads
Installing the deAPI Node
- n8n Cloud: Go to Settings → Community Nodes and toggle the “Verified Community Nodes” option
- Self-hosted: Go to Settings → Community Nodes and install
n8n-nodes-deapi
Configuration
- Add your deAPI credentials (API key + webhook secret)
- Add your Anthropic credentials (API key)
- Add your Google Drive credentials (OAuth2)
- Set the target Google Drive folder ID in the Google Drive Upload node
- Ensure your n8n instance is on HTTPS
How to customize this workflow
- Change the AI model: Swap Anthropic for OpenAI, Google Gemini, or any other LLM provider
- Adjust the prompt style: Modify the AI Agent system message to target different thumbnail aesthetics (minimalist, bold text overlay, cinematic, etc.)
- Change the output destination: Replace Google Drive with Dropbox, S3, Notion, or email delivery
- Add a summary output: Insert a Google Docs or Notion node after the AI Agent to save the written summary alongside the thumbnail
- Process in bulk: Replace the Manual Trigger with a Google Sheets trigger containing a list of YouTube URLs
- Swap the trigger: Use a Form Trigger to let team members submit YouTube URLs through a web form
- Other video platforms: The transcription node also supports Twitch VODs, X (Twitter), and Kick URLs
🔗 Nodes Used
Google Drive, AI Agent, Anthropic Chat Model, Structured Output Parser
📥 Import
Download workflow.json and import into n8n:
Workflow menu → Import from File