Gemini → Generate Video

Overview

This action enables video generation through Google's Gemini API (with models like Veo 3). By providing a prompt and configuring video parameters, you can create unique AI-generated video content via API.

Inputs

Function Stack

1. Gemini API Request
   • Sends a POST request to:

https://generativelanguage.googleapis.com/v1beta/models/{model}

- Passes the prompt and video-specific parameters (aspect ratio, person generation policy) in the body.

2. Precondition
   • Checks for a successful (status 200) response.
3. Response
   • Returns the API response result (including video metadata and download instructions).

Example Usage

Request

{
  "gemini_api_key": "AIzaSyD...",
  "model": "veo-3.0-generate-preview",
  "prompt": "A cinematic wide shot panning over a futuristic city skyline at sunset",
  "aspect_ratio": "16:9",
  "person_generation": "allow_all"
}

Response

{
    "name": "/veo.../.../.."
}

Notes

• The model should be set to the latest supported Gemini video model. Use Veo 3 for best results.
• You can adjust the prompt and configuration for different styles, content, and policies.
• Person generation controls the presence and portrayal of people in the resulting video.
• Download links for generated videos are temporary—be sure to save your files promptly.

Troubleshooting

• PERMISSION_DENIED or INVALID_ARGUMENT: Check your API key, model name, and input parameters.
• Video not returned or incomplete: Simplify your prompt or relax constraints for best performance.
• For current API documentation and supported parameters, reference the Gemini API documentation.