img_uuid, and resolve the asynchronous result by polling or HTTPS callback.Gemini Omni Video API for Image-to-Video Workflows
Access Gemini Omni Video through the independent GoEnhance API. Submit one to seven images with a transformation and sound-design prompt, save the returned
Create an API Key
Gemini Omni Video API Capabilities
Guide with One to Seven Images
Provide one to seven public image URLs in image_urls. Each file can be JPEG, PNG, or WebP up to 20MB; at least one image is required.
Describe Motion and Sound Together
Use the required prompt to describe both the visual transformation and sound design. The documented maximum is 4,096 characters.
Choose Duration, Ratio, and Resolution
Choose 4, 6, 8, or 10 seconds, a 16:9 or 9:16 aspect ratio, and 720p, 1080p, or 4K output. Defaults are 8 seconds, 16:9, and 720p.
Validate required images, prompt length, output enums, and callback URL before submitting a billable task.
Gemini Omni Video API Parameters and Validation
Exact Model ID
Set <code>model</code> to <code>gemini_omni_video</code>. The model, prompt, and image array are required.
One to Seven Image URLs
Send <code>image_urls</code> with 1–7 public JPEG, PNG, or WebP files. Each documented input limit is 20MB.
4,096-Character Prompt
Describe the image transformation and synchronized sound design in <code>prompt</code>; the field is required.
Four Durations
Choose 4, 6, 8, or 10 seconds. If omitted, <code>duration</code> defaults to 8 seconds.
Landscape or Portrait
Set <code>aspect_ratio</code> to <code>16:9</code> or <code>9:16</code>. The documented default is 16:9.
720p, 1080p, or 4K
Set <code>resolution</code> to 720p, 1080p, or 4K. An optional integer <code>seed</code> from 0 to 2,147,483,647 supports repeatable requests.
720p and 1080p share one price table; 4K uses the higher fixed price for the selected duration.
Gemini Omni Video API Pricing
720p and 1080p Pricing
4s: 20.48 tokens ($0.4096); 6s: 27.3 ($0.546); 8s: 34.13 ($0.6826); 10s: 40.95 ($0.819).
4K Pricing
4s: 47.78 tokens ($0.9556); 6s: 54.6 ($1.092); 8s: 61.43 ($1.2286); 10s: 68.25 ($1.365).
Fixed Price per Generation
GoEnhance documents each duration-resolution combination as a fixed token amount using $0.02 per token. Check the live reference before production rollout because pricing can change.
Integrate Gemini Omni Video in Three Steps
1
1. Validate Images and Settings
Create an API key, prepare 1–7 authorized image URLs, write the motion-and-audio prompt, and validate duration, ratio, resolution, seed, and callback URL.
2
2. Submit and Persist img_uuid
POST to
https://api.goenhance.ai/api/v1/videos/generations with bearer authentication and model: gemini_omni_video, then save data.img_uuid. 3
3. Poll or Handle the Callback
Poll
GET https://api.goenhance.ai/api/v1/jobs/detail?img_uuid=... or process callback events idempotently until the task reaches success or failed.Build repeatable workflows around images and creative material you own or are authorized to use.
Gemini Omni Video API Use Cases
Product Image Animation
Turn authorized product stills into short motion concepts with scene-specific sound for review and downstream editing.
Campaign Creative Variants
Parameterize imagery, motion direction, duration, ratio, and resolution for repeatable advertising concept pipelines.
Multi-Reference Story Concepts
Use several approved images to communicate characters, objects, environments, or visual direction in one request.
Audio-Visual Previsualization
Prototype how movement and synchronized native audio might work together before committing to finished production.
Landscape and Vertical Delivery
Generate 16:9 or 9:16 concepts for web, presentation, mobile, and social publishing workflows.
Automated Media Systems
Connect submission, durable task IDs, callbacks, asset storage, moderation, and human approval inside your application.
Answers about Gemini Omni Video API pricing, Google API search intent, image inputs, audio, and asynchronous delivery.