Turn any YouTube video into fast, useful insights your team can use. Enter a video ID and chat with an AI that knows the full transcript and video details. Great for content teams, researchers, and anyone who needs quick answers without watching the whole video.

Behind the scenes, a chat trigger starts a conversation and keeps history so the AI remembers context. A custom tool builds a YouTube Data API request and pulls title, description, and publish date. Code also collects the video transcript, splits it into parts, and combines it into one clean text block. The workflow then merges details and transcript into one JSON object. An AI agent powered by an OpenAI model reads this data and answers questions, summarizes content, and points to key moments.

To set it up, you need a YouTube Data API key from Google Cloud and an OpenAI API key. DeepSeek is optional and can be added if you want more model choices. Expect faster research, less manual viewing time, and better reuse of video content. Common uses include building summaries for blogs, pulling quotes for social posts, and reviewing long training videos in minutes.

• Chat message trigger starts a conversation and captures user input for the AI agent.
• Window Buffer Memory keeps recent chat history so replies stay in context.
• Custom tool fetches video details and transcript on demand from a video ID.
• Code node builds the YouTube Data API URL and pulls official video metadata.
• Transcript fetch with code splits long text into parts and combines them cleanly.
• Merge and Aggregate nodes create one JSON object that includes details and transcript.
• OpenAI chat model with low temperature gives focused, factual answers.
• Can be executed by another workflow, so teams can reuse it across projects.

• Reduce video review time from 60 minutes to about 3 minutes with instant summaries and Q and A
• Automate up to 80 percent of ad hoc content research for marketing and training
• Improve accuracy by using the full transcript and video metadata in every answer
• Handle 10 times more videos per day with the same team size
• Connect AI chat with YouTube Data API and transcript extraction in one place

1. Import the template into n8n: Create a new workflow in n8n > Click the three dots menu > Select 'Import from File' > Choose the downloaded JSON file.
2. You'll need accounts with YouTube Data API, OpenAI and DeepSeek. See the Tools Required section above for links to create accounts with these services.
3. In Google Cloud, enable YouTube Data API v3 and create an API key. Copy the key and keep it safe.
4. In your OpenAI account, create an API key. Copy the key for use in n8n.
5. If using DeepSeek, create a DeepSeek API key. Keep it ready for credential setup.
6. In n8n, open the HTTP Request node named Get YouTube Video Details. In the Credential dropdown, click Create new credential if needed. Add your YouTube Data API key as a query parameter key and test the connection.
7. Open the OpenAI model node. In the Credential dropdown, click Create new credential and paste your OpenAI API key. Name credentials clearly, for example OpenAI Prod.
8. If you plan to use DeepSeek, open the DeepSeek V3 Chat node. Create a new credential and paste the DeepSeek API key. Follow on screen steps to save.
9. Open the node named Workflow Variables. Confirm where the videoId is expected. Make sure the Execute Workflow Trigger example matches your input format.
10. Open the Code node named Create YouTube API URL and confirm the base URL and query fields include part and id along with your API key. Save changes.
11. Run a test with a public video ID. Check the Merge YouTube Details and Transcript node output to confirm both metadata and transcript are present.
12. If you get a 403 error from YouTube, verify API quota and that the key is enabled for YouTube Data API v3. If no transcript returns, try a video with captions or adjust the transcript code to handle missing segments.