🎬 Create step-by-step Markdown guides from YouTube with Apify and OpenAI
⚡ 0 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
Quick overview
This workflow collects a public YouTube tutorial link via an n8n form, uses Apify Frameskim to extract timestamped screenshots and transcript segments, then uses OpenAI to turn each segment into a concise step and returns a downloadable Markdown guide.
How it works
- Receives a YouTube URL (plus optional start time, end time, and step interval) from an n8n form submission.
- Calls the Apify Frameskim actor to generate frames at the chosen interval, returning a screenshot, timestamp, and transcript excerpt for each segment.
- Cleans and numbers the returned frames, keeping only items with an image and transcript text.
- Uses OpenAI to write a short step title and a single-sentence instruction for each frame based only on that transcript excerpt.
- Assembles a Markdown document that includes each step’s instruction, screenshot, and a timestamped YouTube link.
- Converts the Markdown to a guide.md file and returns it to the form completion page as a download.
Setup
- Create an Apify API token and add an HTTP Header Auth credential with
Authorization: Bearer <YOUR_APIFY_TOKEN>for the Apify request. - Add your OpenAI API credentials and ensure the selected model ID (default:
gpt-4o-mini) is available to your account. - Review and adjust the defaults in the guide settings (step interval, max frames, caption language, and Apify cost cap) to fit your use case.
- Open the n8n form and use its hosted URL to submit a public YouTube video (with captions) to generate the guide.
🔗 Nodes Used
HTTP Request, Basic LLM Chain, OpenAI Chat Model, n8n Form Trigger, Convert to File, n8n Form
📥 Import
Download workflow.json and import into n8n:
Workflow menu → Import from File