Kling VIDEO 3.0 Omni - Generate Video (AI Model · By )

API Documentation

API Reference

Videos

Generate Video

Supported Model Code

Loading models...

Kling VIDEO 3.0 Omni (kling-v3-omni)

kling-v3-omni0 models support this endpoint

kling-v3-omni is the flagship Omni-Video model by Kuaishou, integrating the high-fidelity cinematic generation of Kling V3 with advanced multimodal capabilities. It supports multi-shot storytelling, precise element referencing, and complex video editing, making it the ultimate tool for professional, highly controllable, and consistent video production. https://kling.ai/document-api/apiReference/model/OmniVideo

Generate video

https://api.modelstream.ai

POST/v1/video/generations

Authentication

BearerAuth

AuthenticationBearer <token>

All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx

Parameter Location: Header Param

Request Body

application/json

These parameters come from the selected model form_schema. Switching models updates this list and the request example.

Generation Mode

Choose the generation mode. Text to Video: prompt only. Image to Video: upload reference images as first/last frames or scene references. Reference to Video: mix reference images and reference videos (as feature reference or base video) to generate/edit/extend a video. Refer to elements with <<<image_1>>> in the prompt. Only one mode at a time.

prompt*string

Positive and negative descriptions. Use <<<image_1>>> syntax to reference elements. Max 2500 characters.

RequiredExample Value: A majestic cybernetic tiger walking gracefully through a neon-lit futuristic rain forest, with glowing plants reflecting on damp leaves. The scene transitions as the tiger lets out a powerful roar. Ultra-high resolution, cinematic lighting, 8k.

aspect_ratio?string

Output video aspect ratio. Default 16:9.

Example Value: 16:9

Enum/Options:

16:9 (Landscape): 16:99:16 (Portrait): 9:161:1 (Square): 1:1

mode?string

Generation quality mode. Standard is faster, Pro is higher quality, 4K is sharpest.

Example Value: pro

Enum/Options:

Standard Mode (720P): stdProfessional Mode (1080P): pro4K Mode: 4k

duration?number

Video duration in seconds. Standard single-shot values are 5 or 10 seconds; total up to 15 seconds.

Example Value: 5Value Range: 3 ≤ value ≤ 15step: 1

sound?string

Whether to generate native audio matching the visuals. Must be off when a reference video is used.

Example Value: off

Enum/Options:

Off: offOn: on

Response Parameters

application/json

200apiDocs.responses.successCreateVideoGenTask

task_id?string

Parameter description for Task Id

status?string

Parameter description for Status

400apiDocs.responses.badRequestParams

error?object

Parameter description for Error

message?string

Error Message

type?string

Error Type

param?string

Related Parameters

code?string

Error Code

curl -X POST "https://api.modelstream.ai/v1/video/generations" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling-v3-omni",
  "prompt": "A majestic cybernetic tiger walking gracefully through a neon-lit futuristic rain forest, with glowing plants reflecting on damp leaves. The scene transitions as the tiger lets out a powerful roar. Ultra-high resolution, cinematic lighting, 8k.",
  "size": "1920x1080",
  "duration": 5,
  "mode": "pro",
  "metadata": {
    "aspect_ratio": "16:9",
    "sound": "off",
    "watermark_info": {
      "enabled": false
    }
  }
}'

{
  "task_id": "abcd1234efgh",
  "status": "queued"
}

API Documentation

API Reference

Videos

Generate Video

Supported Model Code

Loading models...

Kling VIDEO 3.0 Omni (kling-v3-omni)

kling-v3-omni0 models support this endpoint

Generate video

https://api.modelstream.ai

POST/v1/video/generations

Authentication

BearerAuth

AuthenticationBearer <token>

All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx

Parameter Location: Header Param

Request Body

application/json

These parameters come from the selected model form_schema. Switching models updates this list and the request example.

Generation Mode

prompt*string

Positive and negative descriptions. Use <<<image_1>>> syntax to reference elements. Max 2500 characters.

aspect_ratio?string

Output video aspect ratio. Default 16:9.

Example Value: 16:9

Enum/Options:

16:9 (Landscape): 16:99:16 (Portrait): 9:161:1 (Square): 1:1

mode?string

Generation quality mode. Standard is faster, Pro is higher quality, 4K is sharpest.

Example Value: pro

Enum/Options:

Standard Mode (720P): stdProfessional Mode (1080P): pro4K Mode: 4k

duration?number

Video duration in seconds. Standard single-shot values are 5 or 10 seconds; total up to 15 seconds.

Example Value: 5Value Range: 3 ≤ value ≤ 15step: 1

sound?string

Whether to generate native audio matching the visuals. Must be off when a reference video is used.

Example Value: off

Enum/Options:

Off: offOn: on

Response Parameters

application/json

200apiDocs.responses.successCreateVideoGenTask

task_id?string

Parameter description for Task Id

status?string

Parameter description for Status

400apiDocs.responses.badRequestParams

error?object

Parameter description for Error

message?string

Error Message

type?string

Error Type

param?string

Related Parameters

code?string

Error Code

curl -X POST "https://api.modelstream.ai/v1/video/generations" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling-v3-omni",
  "prompt": "A majestic cybernetic tiger walking gracefully through a neon-lit futuristic rain forest, with glowing plants reflecting on damp leaves. The scene transitions as the tiger lets out a powerful roar. Ultra-high resolution, cinematic lighting, 8k.",
  "size": "1920x1080",
  "duration": 5,
  "mode": "pro",
  "metadata": {
    "aspect_ratio": "16:9",
    "sound": "off",
    "watermark_info": {
      "enabled": false
    }
  }
}'

{
  "task_id": "abcd1234efgh",
  "status": "queued"
}