Automated Video Insight Generation using Gemini - n8n Workflow

• Content creators and managers needing automated summaries of video assets.


• Data analysts utilizing video data for research.


• Users interested in leveraging multimodal AI features within an n8n workflow environment.


• Anyone looking for robust n8n templates for advanced cloud storage operations.

Manually reviewing and summarizing video content is time-consuming. This sophisticated n8n workflow addresses this challenge by creating a scheduled, end-to-end pipeline for video analysis. By integrating Google Drive operations with the Google Gemini 1.5 Pro model, this automation allows users to automatically download large media files, ensure they are ready for processing, and generate detailed, AI-powered summaries.

This specific n8n workflow demonstrates how to handle file management and complex multimodal AI requests, making it one of the most useful n8n templates for scalable content operations. Setting up this n8n automation requires configuration of both Google Drive and Google AI credentials.

This n8n workflow operates on a scheduled basis, ensuring continuous monitoring and processing of video files:

1. Trigger: The process begins with the Schedule Trigger n8n trigger, which initiates the entire automation at predefined intervals (e.g., daily).


2. Download: The Google Drive n8n node (Download Video from Drive) connects to Google Drive to download the target video file, preparing it for subsequent steps.


3. Preparation (LLM Chain): The Basic LLM Chain node prepares the input, integrating with the Google Gemini Chat Model to structure the user prompt, though the actual file handling relies on subsequent HTTP calls.


4. File Status Check: The Check File Status HTTP Request n8n node pings the Gemini API endpoint to confirm that the video file has been successfully uploaded or is ready for processing via a file URI (Note: The file ID must be manually configured or dynamically passed from a prior upload step not explicitly shown in the provided n8n workflow).


5. AI Analysis: The core logic resides in the Analyze Video HTTP Request n8n node. This node sends a POST request to the Gemini 1.5 Pro model endpoint. The request includes the video file URI and a text prompt instructing the AI: "Please analyze the video and provide a summary."


6. Output Formatting: Finally, the Format Analysis Result Set n8n node standardizes and structures the summary returned by the Gemini model, preparing the output for storage or notification.

To deploy this powerful n8n workflow, follow these steps:

1. Import: Copy the provided JSON into your n8n instance using the 'Import Workflow' feature.


2. Google Drive Credentials: Configure the Download Video from Drive n8n node with your Google Drive OAuth2 credentials. You must specify the exact File ID of the video you wish to analyze.


3. Google Gemini Credentials: Configure the Google Gemini Chat Model node with your Google Gemini (PaLM) API credentials.


4. API Keys and Placeholders: Review the Check File Status and Analyze Video HTTP Request n8n node parameters. You must replace the placeholder yourfileid in the URLs and JSON body with the actual File ID referencing the video as processed by the Gemini File API. This step often requires a preceding node (not shown) to upload the file to Gemini's file service.


5. Activation: Once all credentials and parameters are set, activate the n8n trigger and test the n8n workflow to ensure seamless video analysis.

Schedule Trigger (Schedule Trigger)
Function: Serves as the initial n8n trigger, defining when the automation should execute (e.g., hourly, daily).
Key Configuration: Configured for periodic execution.
Download Video from Drive (Google Drive)
Function: Downloads the specified video file from a connected Google Drive account using OAuth2 authentication.
Key Configuration: Requires manual input of the fileId to identify the video.
Basic LLM Chain (LangChain)
Function: Prepares the overall prompt structure for the subsequent AI processing step, leveraging the connected Gemini model.
Key Configuration: Defines the initial prompt: "Hi, could you please prepare the video below..."
Check File Status (HTTP Request)
Function: Checks the status of the file uploaded to the Gemini endpoint before attempting analysis, using a predefined URL pattern. This n8n node is crucial for ensuring API readiness.
Key Configuration: URL is hardcoded to check a file status endpoint, requiring replacement of yourfileid.
Analyze Video (HTTP Request)
Function: Executes the core AI analysis using the Gemini 1.5 Pro model's multimodal capabilities, sending the file URI and the analysis request prompt.
Key Configuration: Uses POST request; includes the instruction "Please analyze the video and provide a summary." and references the file via fileUri: "files/yourfileid".
Format Analysis Result (Set)
* Function: Structures and cleans the JSON output received from the Gemini analysis for clear reporting or downstream tasks. This is the final n8n node in the processing chain.