Kling V3 Omni

Kling V3 Omni is Kuaishou’s latest video generation model, available through the Starrise AI API. The Omni model combines elements, images, videos, and more via prompts for diverse capabilities — supporting text-to-video, image-to-video, video editing, multi-shot scenes, and synchronized sound effect generation.

Key Capabilities

Text-to-video — Generate videos up to 15 seconds from text prompts
Image-to-video — Use reference images as first/last frames to guide video generation
Video editing — Edit existing videos: add/remove elements, change style, color, weather, etc.
Multi-shot scenes — Create up to 6 shots with custom prompt and duration per shot
Sound effects — Optional synchronized video sound effect generation
Flexible aspect ratio — Supports 16:9, 9:16, and 1:1 output formats
Standard & Pro modes — Choose cost-effective standard mode or high-quality pro mode

Quick Example

curl https://ai.alad.com/kling/v1/videos/omni-video \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "kling-v3-omni",
    "prompt": "A cat elegantly walks through a sun-drenched garden, cinematic lighting",
    "duration": "5",
    "mode": "pro",
    "aspect_ratio": "16:9"
  }'

import requests

response = requests.post(
    "https://ai.alad.com/kling/v1/videos/omni-video",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model_name": "kling-v3-omni",
        "prompt": "A cat elegantly walks through a sun-drenched garden, cinematic lighting",
        "duration": "5",
        "mode": "pro",
        "aspect_ratio": "16:9"
    }
)

task = response.json()
print(f"Task ID: {task['task_id']}")

import requests

response = requests.post(
    "https://ai.alad.com/kling/v1/videos/omni-video",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model_name": "kling-v3-omni",
        "prompt": "Make the person in <<<image_1>>> wave to the camera",
        "image_list": [
            {"image_url": "https://example.com/photo.jpg"}
        ],
        "duration": "5",
        "mode": "pro",
        "aspect_ratio": "16:9"
    }
)

task = response.json()
print(f"Task ID: {task['task_id']}")

Query Task Result

After creating a task, use the task ID to query the status:

cURL

curl https://ai.alad.com/kling/v1/videos/text2video/{task_id} \
  -H "Authorization: Bearer YOUR_API_KEY"

Parameters

Parameter	Type	Required	Description
`model_name`	string	No	Model name, default `kling-v3-omni`
`prompt`	string	Conditionally yes	Text prompt (up to 2500 characters), required when `multi_shot` is false
`mode`	string	No	`std` (standard) or `pro` (professional), default `pro`
`aspect_ratio`	string	Conditionally yes	`16:9`, `9:16`, or `1:1`, required when not using first-frame reference or video editing
`duration`	string	No	Video duration `3`–`15` seconds, default `5`
`image_list`	array	No	Reference images (first/last frame, scene, or style references)
`video_list`	array	No	Reference videos (editing or style references)
`element_list`	array	No	Reference elements from the Kling element library
`multi_shot`	boolean	No	Enable multi-shot scene mode, default `false`
`multi_prompt`	array	Conditionally yes	Shot information (1–6 shots), required when `multi_shot` is true
`sound`	string	No	`on` or `off`, whether to generate sound effects, default `off`
`callback_url`	string	No	Callback URL for task status change notifications

API Reference

View the interactive API Playground for Kling V3 Omni.

Quick Start

Models

Resources

Key Capabilities

Quick Example

Query Task Result

Parameters

API Reference

​Key Capabilities

​Quick Example

​Query Task Result

​Parameters

API Reference

Key Capabilities

Quick Example

Query Task Result

Parameters