Skip to Content
Video ModelsGemini Omni

Gemini Omni Video

Overview

Gemini Omni is Google’s released multimodal creation model built to create from different kinds of input, starting with video. Gemini Omni Flash is the first model in the Omni family, supporting practical video generation and editing workflows such as natural language edits, reference-based creation, scene transformation, and coherent visual storytelling.

Test API KEY: key_00000000000000000000000000000000

Endpoints

1. Create Task

Request

POST https://api.pixwithapi.online/api/task/create

Headers

HeaderValueRequired
Content-Typeapplication/jsonYes
Api-Key{API_KEY}Yes

Request Parameters

ParameterTypeRequiredDescription
promptstringYesThe input prompt (e.g., “A cinematic shot of a robot walking through a neon city”)
image_urlsarrayConditionalProvide 1 to 6 images for image-to-video mode. Omit for text-to-video mode.
model_idstringYes2-52
optionsobjectYesConfiguration options for the task
options.prompt_optimizationbooleanYesIf true, all prompt words will be automatically translated into English.
options.aspect_ratiostringYesAspect ratio of the output. Valid values: '16:9' or '9:16'. Default: '16:9'.
options.resolutionstringYesResolution of the output. Valid values: '720p', '1080p', '4K'. Default: '720p'.
options.durationintYesDuration in seconds. Valid values: 4, 6, 8, or 10. Default: 4.

Example Request - Text-to-Video

{ "prompt": "A cinematic shot of a robot walking through a neon city, rain reflections, smooth camera movement", "model_id": "2-52", "options": { "prompt_optimization": true, "aspect_ratio": "16:9", "resolution": "720p", "duration": 4 } }

Example Request - Image-to-Video

{ "prompt": "Transform the reference images into a coherent short video with cinematic camera movement", "image_urls": [ "https://cdn.pixwithapi.online/images/example_reference_1.jpg", "https://cdn.pixwithapi.online/images/example_reference_2.jpg" ], "model_id": "2-52", "options": { "prompt_optimization": true, "aspect_ratio": "16:9", "resolution": "1080p", "duration": 6 } }

Response Parameters

ParameterTypeDescription
codeint1=success, 0=error
messagestringSuccess and failure messages
dataobject
data.task_idstring
data.estimated_timeintEstimated time in seconds

Response

{ "code": 1, "message": "success", "data": { "task_id": "d425ab4dc256f0ebaa84862b9cea8a3d", "estimated_time": 180 } }
Last updated on