curl --request POST \
  --url https://api.modellix.ai/api/v1/kling/kling-v3-omni-video \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "A woman leaves a subway station and walks into a rainy cyberpunk street, then the camera tracks beside her",
  "videos": [
    "https://example.com/source-video.mp4"
  ]
}
'

{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task-v2v-def456",
    "model_id": "model-123",
    "get_result": {
      "method": "GET",
      "url": "https://api.modellix.ai/api/v1/tasks/task-v2v-def456"
    }
  }
}

{
  "code": 400,
  "message": "Invalid parameters: prompt is required when multi_shot is false"
}

{
  "code": 401,
  "message": "Authentication failed: invalid API key"
}

{
  "code": 429,
  "message": "Rate limit exceeded: 100 requests per minute, retry after 60 seconds"
}

{
  "code": 500,
  "message": "Internal server error"
}

Kling V3 Omni Video

[Core Function] Kling V3 Omni Video V2V is a multimodal video-to-video endpoint that edits or restyles existing footage using prompt plus optional image and video references. [Strengths] It focuses on source fidelity and subject consistency for Omni-style edit workflows, combining prompt guidance with images and videos inputs so changes stay grounded in the original clip. [Best For] Highly recommended for: reference-faithful video edits, restyling existing takes, keeping characters or products consistent while changing motion or scene instructions, and short-form post workflows that start from real footage. [Limitations] Do NOT use this model for pure text-to-video from scratch; use Kling V3 T2V, Kling V3 Omni T2V, or Kling V3 Turbo T2V. Do NOT use it when you only have a still image and no source video; use Kling V3 I2V or Kling V3 Omni I2V. Do NOT use it for deep physics-reasoning generation better served by Kling Video O1. [Routing] Choose Kling V3 Omni Video V2V when the user already has video to edit or transform and mentions Omni or multimodal references. Prefer Kling Video O1 when reasoning-heavy generation is the goal rather than source-based editing.

POST

kling

kling-v3-omni-video

curl --request POST \
  --url https://api.modellix.ai/api/v1/kling/kling-v3-omni-video \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "A woman leaves a subway station and walks into a rainy cyberpunk street, then the camera tracks beside her",
  "videos": [
    "https://example.com/source-video.mp4"
  ]
}
'

{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task-v2v-def456",
    "model_id": "model-123",
    "get_result": {
      "method": "GET",
      "url": "https://api.modellix.ai/api/v1/tasks/task-v2v-def456"
    }
  }
}

{
  "code": 400,
  "message": "Invalid parameters: prompt is required when multi_shot is false"
}

{
  "code": 401,
  "message": "Authentication failed: invalid API key"
}

{
  "code": 429,
  "message": "Rate limit exceeded: 100 requests per minute, retry after 60 seconds"
}

{
  "code": 500,
  "message": "Internal server error"
}

Authorizations

Authorization

string

header

required

API Key authentication. Format: Bearer YOUR_API_KEY.

Body

application/json

Kling V3 Omni V2V — category slice of kling-v3-omni. videos required; images optional; element not exposed. Duration 3-15 with no base-video omit rule.

prompt

string

required

Video generation prompt. For custom multi-shot storyboards, use shot n, m, words; shot n, m, words; where n is the shot index (1-6), m is shot duration in seconds (each >= 1s; sum of all shot durations must equal total duration), and words is the per-shot prompt (max 512 characters). Max length 3072 (recommended <= 2500).

Required string length: 1 - 3072

Example:

"shot 1, 2, Transform the source clip into a cinematic sci-fi sequence; shot 2, 3, Camera pushes in on the hero against neon city lights;"

videos

string[]

required

Required reference video list (max 1). Flat URL maps to base video by default.

Required array length: 1 element

Reference video URL or Base64 string.

Minimum string length: 1

multi_shot

boolean

default:true

When true, the model automatically plans multi-shot transitions. When false, generates a single continuous shot.

Example:

true

images

string[]

Optional reference image list (first/last/refer frames flattened as URLs). Max 4 when a reference video is present.

Required array length: 1 - 4 elements

Reference image URL or Base64 string.

Minimum string length: 1

audio

enum<string>

default:off

Whether to generate audio. Official settings.audio: native | original | off. With reference video, native is not allowed; feature video requires off; base video may use original.

Available options:

native,

original,

off

Example:

"off"

resolution

enum<string>

default:720p

Output video resolution.

Available options:

720p,

1080p,

4k

Example:

"1080p"

aspect_ratio

enum<string>

default:16:9

Video aspect ratio. Optional when a reference video is provided.

Available options:

16:9,

9:16,

1:1

Example:

"16:9"

duration

enum<integer>

default:5

Video duration in seconds (3-15).

Available options:

3,

4,

5,

6,

7,

8,

9,

10,

11,

12,

13,

14,

15

Example:

8

Response

Task submitted successfully

code

integer

required

Response code, 0 indicates success

Example:

0

message

string

required

Response message

Example:

"success"

data

object

required

Detailed data about the submitted asynchronous task.

Show child attributes

Model API

Common API

File API

Kling V3 Omni Video

Authorizations

Body

Response