Skip to content
HiAPI Docs
HiAPI
Playground Get API Key
English
English 中文

Gemini Omni 1.1 Flash Video Generation API

POST Base URL: https://api.hiapi.ai /v1/tasks

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model gemini-omni-1.1-flash
Input modes Text and multimodal inputs
Duration 4 / 6 / 8 / 10 seconds
Resolution 360p / 720p / 1080p / 4K

One unified model ID for video generation with text, image, and reference-video inputs.

Production guidance

Calling the API
  • Read data.taskId after creating the task.
  • Wait for callback or poll GET /v1/tasks/:id; read output[].url after success.

Best suited for

Standard video generation

One model ID supports text, image, and reference-video inputs.

promptimage_urlsvideo_list

Request parameters

model string required

Unified model ID.

example gemini-omni-1.1-flash
input object required

Choose text or multimodal inputs for the desired creation mode.

prompt string required

Describe the scene, action, camera, and sound in 1–20,000 characters.

image_urls string[] optional

Optional image URLs, up to 7; use them as source or reference images.

first_frame_url string optional

Optional first-frame image URL; do not combine it with image_urls or video_list.

last_frame_url string optional

Optional last-frame image URL; provide first_frame_url as well.

video_list object[] optional

Optional video input, up to 1 item; video input determines output duration.

url string required

Publicly reachable video URL.

start number optional

Start time in seconds.

default 0
ends number optional

End time in seconds.

duration string optional

Output duration in seconds; video input lets the model determine duration.

default 8 enum: 46810
aspect_ratio enum optional

Output video aspect ratio.

default 16:9 enum: 16:99:16
resolution enum optional

Output video resolution.

default 720p enum: 360p720p1080p4k
seed integer optional

Optional random seed from 0 to 2147483647.

callback object optional

Receive a notification when the task reaches a terminal status.

url string required

HTTPS URL that receives the notification.

when enum optional

Trigger at terminal status.

default final enum: final

Example requests

Reference-video example

Use a permanent target-model video as input for a style and motion transformation.

Request body
{
  "model": "gemini-omni-1.1-flash",
  "input": {
    "prompt": "One continuous shot of a calm golden sunrise over the ocean, with a slow cinematic push-in and natural ambient sound.",
    "video_list": [
      {
        "url": "https://static.hiapi.ai/admin-assets/gemini-omni-1-1-flash/2026/09/02/1788359834997-73681ce500c88b7c-gemini-omni-1-1-flash-golden.mp4",
        "start": 0,
        "ends": 8
      }
    ],
    "duration": "8",
    "aspect_ratio": "16:9",
    "resolution": "720p"
  }
}
Image reference example

Place a publicly reachable image URL in image_urls.

Request body
{
  "model": "gemini-omni-1.1-flash",
  "input": {
    "prompt": "Animate the subject in the reference image with gentle motion.",
    "image_urls": [
      "https://static.hiapi.ai/admin-assets/2026/08/29/1787978094949-d75ee2d6c7d1000d-i2v-watch.png"
    ],
    "duration": "4",
    "aspect_ratio": "16:9",
    "resolution": "360p"
  }
}

Getting the result

  1. Read data.taskId from the create response.
  2. Wait for callback or poll GET /v1/tasks/:id.
  3. When status=success, read output[].url.

FAQ

How many model IDs are exposed?

HiAPI exposes one model ID, gemini-omni-1.1-flash; the input fields determine the creation mode.

How do I retrieve the result?

Use callback or poll GET /v1/tasks/:id.

Next steps