# Kling V3 Omni (kling-v3-omni)

Vendor: KlingAI
Model ID: `kling-v3-omni`
Base URL: `https://api.mulerouter.ai`
Type: Inference API (async task-based)

## Description
Kling V3 Omni video generation model with text-to-video, image-to-video, reference-to-video, and video-to-video capabilities including multi-shot, audio generation, element references, and 3-15s duration support

## Variant: Video to Video Edit

Endpoint: `POST /vendors/klingai/v1/kling-v3-omni/video-to-video/edit`

### Input Schema
The API accepts the following input parameters:

- **`mode`** (`string`, _optional_):
  Generation mode. std for standard quality (720P), pro for higher quality (1080P).
  - Options: `"std"`, `"pro"`
  - Default: `"pro"`

- **`video`** (`string`, _required_):
  Video URL to edit.

- **`images`** (`list<string>`, _optional_):
  Optional list of reference image URLs or Base64 strings.

- **`prompt`** (`string`, _required_):
  Text prompt describing the desired edit. Use @Video1 to reference the input video.
  - Max length: 2500

- **`elements`** (`list<any>`, _optional_):
  Element list. Combined count of images and elements must not exceed 4 when using reference video.
  - Items: max: 4

  - **`type`** (`string`, _required_):
    Element type.
    - Options: `"image"`, `"video"`

  - **`frontal_image`** (`string | null`, _optional_):
    Frontal reference image of the subject (URL or Base64). Constraints: jpg/jpeg/png, <=10MB, >=300px, aspect ratio 1:2.5~2.5:1.

  - **`reference_images`** (`list<string>`, _optional_):
    Additional reference images from other angles (URL or Base64), up to 3 images.
    - Items: min: 1, max: 3

  - **`reference_videos`** (`list<string>`, _optional_):
    Reference video URLs.
    - Items: min: 1

- **`aspect_ratio`** (`string | null`, _optional_):
  Aspect ratio of the generated video.

- **`negative_prompt`** (`string | null`, _optional_):
  Negative prompt to exclude unwanted content.

**Required Parameters Example**:

```json
{
  "prompt": "<Text prompt describing the desired edit>",
  "video": "<Video URL to edit>"
}
```

**Full Example**:

```json
{
  "mode": "pro",
  "video": "<Video URL to edit>",
  "images": [],
  "prompt": "<Text prompt describing the desired edit>",
  "elements": [],
  "aspect_ratio": null,
  "negative_prompt": null
}
```

## Variant: Text to Video Generation

Endpoint: `POST /vendors/klingai/v1/kling-v3-omni/text-to-video/generation`

### Input Schema
The API accepts the following input parameters:

- **`mode`** (`string`, _optional_):
  Generation mode. std for standard quality, pro for higher quality.
  - Options: `"std"`, `"pro"`
  - Default: `"pro"`

- **`sound`** (`string`, _optional_):
  Whether to generate sound for the video.
  - Options: `"on"`, `"off"`
  - Default: `"off"`

- **`prompt`** (`string | null`, _optional_):
  Text prompt describing the video to generate. Either prompt or multi_prompt must be provided.

- **`duration`** (`integer`, _optional_):
  Duration of the generated video in seconds (3-15).
  - Default: `5`

- **`elements`** (`list<any>`, _optional_):
  Element list. Combined count of images and elements must not exceed 7.
  - Items: max: 7

  - **`type`** (`string`, _required_):
    Element type.
    - Options: `"image"`, `"video"`

  - **`frontal_image`** (`string | null`, _optional_):
    Frontal reference image of the subject (URL or Base64). Constraints: jpg/jpeg/png, <=10MB, >=300px, aspect ratio 1:2.5~2.5:1.

  - **`reference_images`** (`list<string>`, _optional_):
    Additional reference images from other angles (URL or Base64), up to 3 images.
    - Items: min: 1, max: 3

  - **`reference_videos`** (`list<string>`, _optional_):
    Reference video URLs.
    - Items: min: 1

- **`shot_type`** (`string | null`, _optional_):
  Shot type configuration.

- **`multi_shot`** (`boolean`, _optional_):
  Whether to enable multi-shot generation.
  - Default: `false`

- **`aspect_ratio`** (`string | null`, _optional_):
  Aspect ratio of the generated video.

- **`multi_prompt`** (`list<any>`, _optional_):
  Multi-segment prompts for finer control. Either prompt or multi_prompt must be provided.
  - Items: min: 1, max: 6

  - **`prompt`** (`string`, _required_):
    - Max length: 512

  - **`duration`** (`integer`, _required_):

- **`negative_prompt`** (`string | null`, _optional_):
  Negative prompt to exclude unwanted content.

**Full Example**:

```json
{
  "mode": "pro",
  "sound": "off",
  "prompt": null,
  "duration": 5,
  "elements": [],
  "shot_type": null,
  "multi_shot": false,
  "aspect_ratio": null,
  "multi_prompt": [],
  "negative_prompt": null
}
```

## Variant: Image to Video Generation

Endpoint: `POST /vendors/klingai/v1/kling-v3-omni/image-to-video/generation`

### Input Schema
The API accepts the following input parameters:

- **`mode`** (`string`, _optional_):
  Generation mode. std for standard quality, pro for higher quality.
  - Options: `"std"`, `"pro"`
  - Default: `"pro"`

- **`sound`** (`string`, _optional_):
  Whether to generate sound for the video.
  - Options: `"on"`, `"off"`
  - Default: `"off"`

- **`images`** (`array | null`, _optional_):
  List of reference image URLs or Base64 strings.

- **`prompt`** (`string | null`, _optional_):
  Text prompt to guide video generation from the images.

- **`duration`** (`integer`, _optional_):
  Duration of the generated video in seconds (3-15).
  - Default: `5`

- **`elements`** (`list<any>`, _optional_):
  Element list. Max 3 when using first/last frame images.
  - Items: max: 3

  - **`type`** (`string`, _required_):
    Element type.
    - Options: `"image"`, `"video"`

  - **`frontal_image`** (`string | null`, _optional_):
    Frontal reference image of the subject (URL or Base64). Constraints: jpg/jpeg/png, <=10MB, >=300px, aspect ratio 1:2.5~2.5:1.

  - **`reference_images`** (`list<string>`, _optional_):
    Additional reference images from other angles (URL or Base64), up to 3 images.
    - Items: min: 1, max: 3

  - **`reference_videos`** (`list<string>`, _optional_):
    Reference video URLs.
    - Items: min: 1

- **`shot_type`** (`string | null`, _optional_):
  Shot type configuration.

- **`last_frame`** (`string | null`, _optional_):
  Last frame image (URL or Base64). Sets the closing frame of the generated video.

- **`multi_shot`** (`boolean`, _optional_):
  Whether to enable multi-shot generation.
  - Default: `false`

- **`first_frame`** (`string | null`, _optional_):
  First frame image (URL or Base64). Sets the opening frame of the generated video.

- **`aspect_ratio`** (`string | null`, _optional_):
  Aspect ratio of the generated video.

- **`multi_prompt`** (`list<any>`, _optional_):
  Multi-segment prompts for finer control.
  - Items: min: 1, max: 6

  - **`prompt`** (`string`, _required_):
    - Max length: 512

  - **`duration`** (`integer`, _required_):

- **`negative_prompt`** (`string | null`, _optional_):
  Negative prompt to exclude unwanted content.

**Full Example**:

```json
{
  "mode": "pro",
  "sound": "off",
  "images": null,
  "prompt": null,
  "duration": 5,
  "elements": [],
  "shot_type": null,
  "last_frame": null,
  "multi_shot": false,
  "first_frame": null,
  "aspect_ratio": null,
  "multi_prompt": [],
  "negative_prompt": null
}
```

## Variant: /vendors/klingai/v1/kling-v3-omni/video-to-video/edit/{task_id}

Endpoint: `POST /vendors/klingai/v1/kling-v3-omni/video-to-video/edit/{task_id}`

## Variant: /vendors/klingai/v1/kling-v3-omni/text-to-video/generation/{task_id}

Endpoint: `POST /vendors/klingai/v1/kling-v3-omni/text-to-video/generation/{task_id}`

## Variant: /vendors/klingai/v1/kling-v3-omni/image-to-video/generation/{task_id}

Endpoint: `POST /vendors/klingai/v1/kling-v3-omni/image-to-video/generation/{task_id}`

## Variant: Reference Image to Video Generation

Endpoint: `POST /vendors/klingai/v1/kling-v3-omni/reference-image-to-video/generation`

### Input Schema
The API accepts the following input parameters:

- **`mode`** (`string`, _optional_):
  Generation mode. std for standard quality, pro for higher quality.
  - Options: `"std"`, `"pro"`
  - Default: `"pro"`

- **`sound`** (`string`, _optional_):
  Whether to generate sound for the video.
  - Options: `"on"`, `"off"`
  - Default: `"off"`

- **`images`** (`list<string>`, _optional_):
  List of reference image URLs or Base64 strings.

- **`prompt`** (`string | null`, _optional_):
  Text prompt to guide video generation.

- **`duration`** (`integer`, _optional_):
  Duration of the generated video in seconds (3-15).
  - Default: `5`

- **`elements`** (`list<any>`, _optional_):
  Element list. Combined count of images and elements must not exceed 7.
  - Items: max: 7

  - **`type`** (`string`, _required_):
    Element type.
    - Options: `"image"`, `"video"`

  - **`frontal_image`** (`string | null`, _optional_):
    Frontal reference image of the subject (URL or Base64). Constraints: jpg/jpeg/png, <=10MB, >=300px, aspect ratio 1:2.5~2.5:1.

  - **`reference_images`** (`list<string>`, _optional_):
    Additional reference images from other angles (URL or Base64), up to 3 images.
    - Items: min: 1, max: 3

  - **`reference_videos`** (`list<string>`, _optional_):
    Reference video URLs.
    - Items: min: 1

- **`shot_type`** (`string | null`, _optional_):
  Shot type configuration.

- **`last_frame`** (`string | null`, _optional_):
  Last frame image (URL or Base64). Sets the closing frame of the generated video.

- **`multi_shot`** (`boolean`, _optional_):
  Whether to enable multi-shot generation.
  - Default: `false`

- **`first_frame`** (`string | null`, _optional_):
  First frame image (URL or Base64). Sets the opening frame of the generated video.

- **`aspect_ratio`** (`string | null`, _optional_):
  Aspect ratio of the generated video.

- **`multi_prompt`** (`list<any>`, _optional_):
  Multi-segment prompts for finer control.
  - Items: min: 1, max: 6

  - **`prompt`** (`string`, _required_):
    - Max length: 512

  - **`duration`** (`integer`, _required_):

- **`negative_prompt`** (`string | null`, _optional_):
  Negative prompt to exclude unwanted content.

**Full Example**:

```json
{
  "mode": "pro",
  "sound": "off",
  "images": [],
  "prompt": null,
  "duration": 5,
  "elements": [],
  "shot_type": null,
  "last_frame": null,
  "multi_shot": false,
  "first_frame": null,
  "aspect_ratio": null,
  "multi_prompt": [],
  "negative_prompt": null
}
```

## Variant: Reference Video to Video Generation

Endpoint: `POST /vendors/klingai/v1/kling-v3-omni/reference-video-to-video/generation`

### Input Schema
The API accepts the following input parameters:

- **`mode`** (`string`, _optional_):
  Generation mode. std for standard quality, pro for higher quality.
  - Options: `"std"`, `"pro"`
  - Default: `"pro"`

- **`video`** (`string`, _required_):
  Reference video URL.

- **`prompt`** (`string`, _required_):
  Text prompt describing the desired transformation.
  - Max length: 2500

- **`duration`** (`integer`, _optional_):
  Duration of the generated video in seconds (3-15).
  - Default: `5`

- **`elements`** (`list<any>`, _optional_):
  Element list. Combined count of images and elements must not exceed 4 when using reference video.
  - Items: max: 4

  - **`type`** (`string`, _required_):
    Element type.
    - Options: `"image"`, `"video"`

  - **`frontal_image`** (`string | null`, _optional_):
    Frontal reference image of the subject (URL or Base64). Constraints: jpg/jpeg/png, <=10MB, >=300px, aspect ratio 1:2.5~2.5:1.

  - **`reference_images`** (`list<string>`, _optional_):
    Additional reference images from other angles (URL or Base64), up to 3 images.
    - Items: min: 1, max: 3

  - **`reference_videos`** (`list<string>`, _optional_):
    Reference video URLs.
    - Items: min: 1

- **`keep_audio`** (`boolean`, _optional_):
  Whether to keep the audio from the source video.
  - Default: `false`

- **`aspect_ratio`** (`string | null`, _optional_):
  Aspect ratio of the generated video.

- **`negative_prompt`** (`string | null`, _optional_):
  Negative prompt to exclude unwanted content.

**Required Parameters Example**:

```json
{
  "prompt": "<Text prompt describing the desired trans>",
  "video": "<Reference video URL>"
}
```

**Full Example**:

```json
{
  "mode": "pro",
  "video": "<Reference video URL>",
  "prompt": "<Text prompt describing the desired trans>",
  "duration": 5,
  "elements": [],
  "keep_audio": false,
  "aspect_ratio": null,
  "negative_prompt": null
}
```

## Variant: /vendors/klingai/v1/kling-v3-omni/reference-image-to-video/generation/{task_id}

Endpoint: `POST /vendors/klingai/v1/kling-v3-omni/reference-image-to-video/generation/{task_id}`

## Variant: /vendors/klingai/v1/kling-v3-omni/reference-video-to-video/generation/{task_id}

Endpoint: `POST /vendors/klingai/v1/kling-v3-omni/reference-video-to-video/generation/{task_id}`

## Usage (Async Task API)
This model uses an async task-based workflow with two API calls:
1. **Submit a task** — `POST /v1/inference/kling-v3-omni` to create a generation task
2. **Poll for result** — `GET /v1/inference/kling-v3-omni/{task_id}` to check status and retrieve the result

### Step 1: Submit a Task

#### cURL
```bash
curl -X POST https://api.mulerouter.ai/vendors/klingai/v1/kling-v3-omni/video-to-video/edit \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <YOUR_MULEROUTER_API_KEY>" \
  -d '{
    "prompt": "Your prompt here"
  }'
```

#### Python
```python
import requests

API_KEY = "<YOUR_MULEROUTER_API_KEY>"
ENDPOINT = "https://api.mulerouter.ai/vendors/klingai/v1/kling-v3-omni/video-to-video/edit"

response = requests.post(
    ENDPOINT,
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {API_KEY}"
    },
    json={
        "prompt": "Your prompt here"
    }
)

result = response.json()
task_id = result["task_info"]["id"]
print(f"Task created: {task_id}")
```

#### Node.js / TypeScript
```typescript
const API_KEY = "<YOUR_MULEROUTER_API_KEY>";
const ENDPOINT = "https://api.mulerouter.ai/vendors/klingai/v1/kling-v3-omni/video-to-video/edit";

const response = await fetch(ENDPOINT, {
    method: "POST",
    headers: {
        "Content-Type": "application/json",
        "Authorization": `Bearer ${API_KEY}`
    },
    body: JSON.stringify({
        prompt: "Your prompt here"
    })
});

const result = await response.json();
const taskId = result.task_info.id;
console.log("Task created:", taskId);
```

#### Submit Response (202)
```json
{
  "task_info": {
    "id": "8e1e315e-b50d-4334-a231-be7d19a372f4",
    "status": "processing",
    "created_at": "2026-01-01T00:00:00.000Z"
  }
}
```

### Step 2: Poll for Result

Use the task ID from Step 1 to poll the status endpoint until the task is completed.

Endpoint: `GET /v1/inference/kling-v3-omni/{task_id}`

#### cURL
```bash
curl -X GET https://api.mulerouter.ai/vendors/klingai/v1/kling-v3-omni/video-to-video/edit/<TASK_ID> \
  -H "Authorization: Bearer <YOUR_MULEROUTER_API_KEY>"
```

#### Python
```python
import time

status_url = f"https://api.mulerouter.ai/vendors/klingai/v1/kling-v3-omni/video-to-video/edit/{task_id}"

while True:
    status = requests.get(status_url, headers={
        "Authorization": f"Bearer {API_KEY}"
    }).json()
    task_status = status["task_info"]["status"]
    if task_status in ("completed", "succeeded"):
        print("Result:", status)
        break
    elif task_status == "failed":
        print("Task failed:", status)
        break
    time.sleep(5)
```

#### Node.js / TypeScript
```typescript
const statusUrl = `https://api.mulerouter.ai/vendors/klingai/v1/kling-v3-omni/video-to-video/edit/${taskId}`;

while (true) {
    const statusRes = await fetch(statusUrl, {
        headers: { "Authorization": `Bearer ${API_KEY}` }
    });
    const status = await statusRes.json();
    const taskStatus = status.task_info.status;
    if (taskStatus === "completed" || taskStatus === "succeeded") {
        console.log("Result:", status);
        break;
    } else if (taskStatus === "failed") {
        console.log("Task failed:", status);
        break;
    }
    await new Promise(r => setTimeout(r, 5000));
}
```

## Additional Resources

### Documentation

- [Model Playground](https://www.mulerouter.ai/models/kling-v3-omni)
- [API Documentation](https://mulerouter.ai/docs/api-reference/endpoint/klingai/kling-v3-omni)

### MuleRouter Platform

- [Platform Documentation](https://www.mulerouter.ai/docs)
- [API Keys Management](https://www.mulerouter.ai/app/api-keys)