AI Summary and Lesson Extraction from YouTube Transcripts to Google Docs - n8n Workflow

• Content creators and researchers who need fast summaries of video content.


• Teams looking to integrate external data (like video transcripts) into their documentation pipeline.


• Users interested in leveraging advanced AI models within an n8n workflow.


• Developers seeking robust n8n templates for custom data extraction.

Managing vast amounts of video content can be time-consuming. This specialized n8n workflow solves the problem of manual transcription and summarization by automating the entire process. It uses a simple chat message containing a YouTube URL as the initial n8n trigger. The n8n automation then fetches the full transcript via the Supadata API. The core intelligence relies on an advanced n8n node setup utilizing the Gemini AI model (via OpenRouter) to not just summarize, but to extract structured data like key lessons and facts. The final output is saved immediately into a Google Doc, making it an excellent productivity-enhancing n8n template for knowledge workers. This complex n8n workflow demonstrates powerful API integration combined with flexible LLM prompting.

This automation is initiated by a simple chat message, acting as the primary n8n trigger.

1. Start via n8n Trigger: The When chat message received n8n node starts the process upon receiving a YouTube URL.


2. API Key Configuration: The Set your supadata key n8n node prepares the required API authentication key for the next step.


3. Fetch Transcript: The supadata API - YouTube endpoint n8n node makes an HTTP request, utilizing the URL from the n8n trigger to retrieve the video transcript data.


4. Process Data: The transcript is often structured across multiple rows. The Split Out n8n node breaks the data into individual items, and the Aggregate n8n node combines all these transcript fragments into a single, cohesive text block, preparing it for AI processing.


5. AI Transformation: The aggregated text is passed to the Proces transcript to summary template n8n node (a Chain LLM). This n8n node applies detailed instructions, demanding a brief summary, lessons learned (bullet points), and interesting facts, all formatted in Markdown.


6. LLM Execution: The Gemini 2.0 flash n8n node (using OpenRouter credentials) connects to the template n8n node, executing the prompt and generating the high-quality, structured summary.


7. Save to Google Docs: Finally, the Create new Google Doc with summary Google Drive n8n node takes the AI-generated output and automatically creates a new document on your drive, completing this highly efficient n8n workflow.

To deploy this comprehensive n8n workflow, follow these steps:

1. Import: Copy the provided JSON code and paste it into your n8n instance using the 'Import from JSON' function.


2. Credentials Setup: You will need to configure credentials for the following services:

1. API Key Configuration: In the Set your supadata key n8n node, replace the placeholder value with your actual Supadata API key. This is crucial for the n8n workflow to fetch the transcripts.


2. Activate: Save the n8n workflow and set the toggle to 'Active' to enable the chat n8n trigger.

When chat message received (Chat Trigger n8n trigger):
Function: Starts the n8n workflow upon receiving a message, which is expected to be the YouTube URL.
Key Configuration: Acts as the entry point, passing the chat input as chatInput.
Set your supadata key (Set n8n node):
Function: Securely injects the necessary API key into the workflow data stream, naming it supadatakey.
supadata API - YouTube endpoint (HTTP Request n8n node):
Function: Calls the external Supadata service to get the transcript data based on the dynamic URL provided by the n8n trigger.
Key Configuration: URL is dynamically constructed using the input chatInput.
Split Out / Aggregate (Data Processing n8n nodes):
Function: These standard n8n nodes normalize the transcript data, converting the API's array response into a single, clean text string under the field name text for efficient LLM consumption.
Proces transcript to summary template (Chain LLM n8n node):
Function: Defines the precise instructions (the prompt template) for the AI, guiding it to summarize and extract lessons, ensuring the output is always in Markdown.
Gemini 2.0 flash (LLM Chat OpenRouter n8n node):
Function: Provides the LLM backend for the summarization task. Uses the specified google/gemini-2.0-flash-001 model.
Create new Google Doc with summary (Google Drive n8n node):
Function: Creates the final persistence layer for the structured AI output, saving the summary directly to a Google Document.
* Key Configuration: Document name includes a timestamp ({{ $now }}) for unique identification.