Dive into the future of video processing directly within your n8n workflows! I'm excited to introduce the Video AI Analysis Node, a powerful community node designed to bring advanced artificial intelligence capabilities to your video files.
Created by HadidizFlow | Follow on YouTube
This node acts as your bridge to powerful AI models, allowing you to analyze video content in various ways. Simply provide a video URL and a custom prompt, and let the AI handle the rest. Think of operations like generating concise summaries of video content, creating reviews based on video footage, extracting key insights or descriptions from scenes, generating transcripts (depending on the AI model's capability), and much more, driven by your custom prompts!
Beta Note: Currently, the node exclusively supports Google Gemini models. We're actively working on integrating more AI providers to give you even greater flexibility in the future!
You can add the Video AI node to your n8n instance easily.
Navigate to Settings in your n8n instance. Select Community Nodes. Click Install. Search for
n8n-nodes-video-ai click Install again.
If you're self-hosting n8n and have command-line access, you can install it via npm: npm install n8n-nodes-video-ai. Remember to restart your n8n instance after installation.
Using the node involves a few simple steps:
Step 1: Add the Node
Find the "Video AI Analysis" node in the n8n nodes panel and drag it onto your workflow canvas.
Step 2: Configure Credentials
Since we currently support Google Gemini, you'll need Gemini API credentials. In n8n, go to the Credentials section. Click Add Credential. Search for "Gemini API" and select it. Enter your Google Gemini API key. You can get one from the Google AI Studio. Save the credential with a recognizable name. Back in the node configuration, select the credential you just created from the dropdown menu.
Step 3: Provide the Video URL
In the "Video URL" field, paste the direct URL to the video file you want to analyze. Ensure it's a publicly accessible link to the video file itself (e.g., ending in .mp4, .mov).
Step 4: Write Your Custom Prompt
This is where you tell the AI what to do. In the "Custom Prompt" field, write clear instructions. Examples: Summarize the key points discussed in this meeting recording., Describe the visual elements and mood of this scene., Generate a list of topics covered in this tutorial video.
Step 5: Select the AI Model
Choose the specific Google Gemini model you wish to use from the "Model" dropdown. Different models have varying capabilities and costs.
Step 6: Configure Options (Optional)
Adjust parameters like "Temperature" (for randomness in the output) or "Maximum Video Size" if needed.
Step 7: Run the Node!
Execute the node. The AI's analysis result will be available in the output data under the text field.
This node has been tested with n8n version 1.85.4 and later.
The source code is available on GitHub. Contributions and feedback are welcome! View on GitHub
Happy Automating!
- HadidizFlow @ HadidizFlow.com
Our cutting-edge features simplify collaboration and creativity, making your workflow intuitive and efficient. Transform your vision into reality effortlessly with Hadidiz Flow.
