Generate YouTube Video Summaries from Transcripts - n8n Workflow

Users looking for advanced LangChain integration techniques using n8n templates.
Content analysts needing quick, automated summaries of long YouTube videos.
Developers building AI-powered content analysis n8n workflow solutions.
Anyone needing an example of how to combine external APIs (SearchAPI) with LLMs in a single n8n node automation.

This comprehensive n8n workflow provides a robust solution for content analysis by automatically summarizing long-form YouTube videos. It leverages the specialized SearchAPI n8n node to accurately retrieve timed transcripts. Due to the inherent length constraints of Large Language Models (LLMs), the n8n workflow intelligently processes the raw transcript data. It aggregates the segments and then employs a LangChain Summarization Chain n8n node, coupled with a Recursive Character Text Splitter n8n node, to handle multi-chunk summarization efficiently. This n8n workflow is a prime example of leveraging specialized n8n templates to build complex, reliable AI operations. Using this specific n8n workflow saves significant time compared to manual summarization.

1. Trigger: The n8n workflow starts manually using the When clicking ‘Test workflow’ n8n trigger, ideal for testing this powerful n8n template.


2. Fetch Transcript: The SearchAPI n8n node is executed, querying the youtubetranscripts engine for the defined videoid (e.g., 2XTdEG0Sus0). This n8n node requires valid SearchAPI credentials.


3. Prepare Data: The Split Out n8n node breaks down the transcript array structure into separate items, preparing the data for the next n8n node.


4. Concatenate Text: The Summarize n8n node aggregates all the individual transcript segments back into one cohesive piece of text, ready for LLM processing by the next n8n node.


5. Define LLM: The OpenRouter Chat Model n8n node configures the specific LLM connection and model used for summary generation (Qwen 0.6B model in this n8n workflow).


6. Set Splitter: The Recursive Character Text Splitter n8n node is configured to break the large concatenated transcript into manageable chunks (6000 character size) before summarization, ensuring the LangChain n8n node handles the data efficiently.


7. Generate Summary: Finally, the Summarization Chain n8n node processes the entire text using the provided LLM and Text Splitter, resulting in a concise summary of the video content. This powerful n8n workflow completes the process automatically.

1. Import the n8n workflow: Copy the provided JSON code and paste it directly into your n8n instance using the "New" -> "Import from JSON" option.


2. SearchAPI Credentials: You must set up credentials for the SearchAPI n8n node. You will need a SearchAPI account and API key to enable the transcript fetching service.


3. OpenRouter/LLM Credentials: Set up credentials for the OpenRouter Chat Model n8n node. This requires an OpenRouter API key.


4. Configuration: Update the SearchAPI n8n node's parameters, specifically the video_id, to target the YouTube video you wish to summarize. This ensures the n8n workflow targets the correct content.


5. Execution: After securing credentials and configuring the video ID, execute the n8n workflow manually using the "Test workflow" button in the When clicking ‘Test workflow’ n8n trigger node. This n8n template is designed for immediate use.

When clicking ‘Test workflow’ (n8n trigger): A manual n8n trigger used for immediate testing and deployment of this specific n8n workflow.
SearchAPI (Custom n8n node): Function: Fetches the raw transcription data for a specified YouTube video ID. Key Configuration: Engine set to youtubetranscripts, targeted videoid is 2XTdEG0Sus0.
Split Out (n8n node): Function: Normalizes the input structure by splitting the transcripts array into individual items, preparing the data for aggregation within the n8n workflow.
Summarize (n8n node): Function: Concatenates the individual text fields from the transcript items into a single, large text string, providing crucial input for the downstream LLM n8n node.
OpenRouter Chat Model (LangChain n8n node): Function: Defines the specific LLM connection and model used for summarization. Key Configuration: Uses the qwen/qwen3-0.6b-04-28:free model via OpenRouter API credentials.
Recursive Character Text Splitter (LangChain n8n node): Function: Ensures that the long transcript is properly segmented (chunked at 6000 characters) before being fed into the summarization n8n node, mitigating LLM token limit errors.

• Summarization Chain (LangChain n8n node): Function: Orchestrates the multi-step summarization process, utilizing the connected LLM model and text splitter to produce the final summary from the concatenated transcript data, completing this crucial n8n workflow step.