Automate YouTube Video Summaries Using n8n and LangChain

What this workflow does

This workflow takes a YouTube video ID and fetches its transcript automatically.
Then, it splits the long transcript into smaller parts.
It uses an AI model to create a clear summary and example questions with answers.
The result helps users get key points and prepare for discussions quickly.

This saves many hours of work from reading or listening to full videos.

Who should use this workflow

People who create content from YouTube videos can use this.
It suits podcasters, educators, or anyone making summaries and Q&A.

No deep technical skills are needed to run this once set up.

Tools and services used

• n8n platform: Runs and orchestrates the workflow.
• OpenAI API: Uses GPT models to process and summarize text.
• SearchApi.io API: Fetches YouTube video transcripts.
• LangChain library: Manages text splitting and summarization chains.

Beginner step-by-step: How to build this in n8n

Step 1: Import the workflow

1. Use the Download button on this page to get the workflow file.
2. Open the n8n editor.
3. Click “Import from File” and select the downloaded workflow.

Step 2: Configure credentials and IDs

1. Add your OpenAI API Key in the OpenAI Chat Model node.
2. Add your SearchApi.io API Key in the LangChain Code node code.
3. Update the YouTube video ID in the Set YouTube video ID node if you want another video summary.

Step 3: Test the workflow

1. Click the Manual Trigger node and select “Execute Workflow.”
2. Confirm you see summary and question outputs.

Step 4: Activate for production

1. Set your trigger node as needed (e.g., Cron) for repeating runs.
2. Save and activate the workflow.

If using self hosting n8n, consider self-host n8n for privacy and better control.

Inputs, Processing Steps, and Outputs

Inputs

• YouTube video ID string.
• OpenAI API Key for language model.
• SearchApi.io API Key for transcript loading.

Processing Steps

• The LangChain Code node uses SearchApiLoader to load the YouTube transcript for given ID.
• Transcript text is split by TokenTextSplitter to handle big text.
• OpenAI GPT model summarizes each chunk and refines the summary with example questions and answers.
• The final output is compiled summary plus example Q&A.

Outputs

• Text summary of the full podcast or interview.
• A list of specific example questions with answers related to the video.

Common problems and solutions

Error: “Please add your API key for searchapi.io to this node”

Means the placeholder API key was not changed in the LangChain Code node.
Fix by editing that code line with your valid SearchApi.io API key.

No transcript found or empty summary output

May happen if YouTube video ID is incorrect or video has no transcript.
Verify video ID and check if transcript is available.

OpenAI API errors or timeouts

Can be cause by invalid API key or network issues.
Check OpenAI API key and internet connection.

Customization ideas

• Change YouTube video ID anytime to summarize other videos.
• Tweak chunkSize and chunkOverlap in LangChain Code node to adjust summary length.
• Select different GPT models in OpenAI Chat Model node for faster or deeper summaries.
• Edit prompt templates in LangChain Code node for a different summary style or question type.
• Add nodes to save summaries to Google Sheets or send emails automatically.

Summary of benefits

→ Get automated video summaries and questions fast.
→ Save many hours of manual summarizing.
→ Use easy n8n workflow with simple API key setup.
→ Focus on content creation instead of reading transcripts.
→ Scale summarizing for many videos by changing IDs.