This n8n workflow automates the process of generating and updating chapters for a YouTube video based on its captions. Designed for content creators and channel managers, the workflow extracts automated captions from a given YouTube video, analyzes the transcript to identify key sections, and updates the video description with structured chapters for improved viewer navigation.

The process begins with a manual trigger, which initiates the workflow. It sets a specific video ID to work with, then retrieves the video’s metadata and captions using YouTube API nodes authenticated with OAuth2. The captions are extracted in SRT format and processed to parse the textual content.

Leveraging language models, the workflow classifies parts of the transcript into chapters with timestamps, then formats this information into an organized chapter list. This list is embedded into the video description by updating the video details via the YouTube API. Additionally, the workflow tags the video with the chapters’ timestamps to enhance searchability.

This automation is useful for YouTube creators seeking to enhance viewer experience through better navigation, and saves significant manual effort in editing and structuring video descriptions for long-form content.

Node Count	11 – 20 Nodes
Nodes Used	@n8n/n8n-nodes-langchain.chainLlm, @n8n/n8n-nodes-langchain.lmChatGoogleGemini, @n8n/n8n-nodes-langchain.outputParserStructured, extractFromFile, httpRequest, manualTrigger, set, stickyNote, youTube