---
title: Kling VIDEO 3.0 Pro | Runware Docs
url: https://runware.ai/docs/models/klingai-video-3-0-pro
description: High-fidelity multimodal video generation with native audio and advanced editing
---
# Kling VIDEO 3.0 Pro

![Kling VIDEO 3.0 Pro](https://assets.runware.ai/covers/klingai-video-3-0-pro.jpg)

Kling VIDEO 3.0 Pro is a unified multimodal video model that generates high-quality video with synchronized audio from text or images. It supports reference-guided generation, prompt-based editing, fine control over motion and pacing, and stable temporal coherence for cinematic and narrative clips. Native audio output includes dialogue, ambient sound, and effects aligned to the visuals.

- **Status**: live
- **ID**: `klingai:kling-video@3-pro`
- Try in Playground
- **Creator**: Kling AI
- **Release Date**: February 5, 2026
- **Capabilities**: Text to Video, Image to Video, Video to Video, Checkpoint, Audio

## Pricing

$0.112 from, per second · ~3m 26s per request

**Rates** (per second)

- 1080p · no audio: `$0.112`
- 1080p · audio: `$0.168`
- 1080p · motion control: `$0.168`

**6 example generations**

- [first-frame](https://runware.ai/docs/models/klingai-video-3-0-pro/examples#example-precision-seed-singulator-demo) · 6s: `$0.672` (~1m 39s)
- [elements](https://runware.ai/docs/models/klingai-video-3-0-pro/examples#example-drained-pool-art-pop-music-video) · 7s: `$0.784` (~7m 16s)
- [text-to-video](https://runware.ai/docs/models/klingai-video-3-0-pro/examples#example-passive-floodgate-mechanism-demo) · 1080p · 5s: `$0.84` (~3m 29s)
- [first-last-frame](https://runware.ai/docs/models/klingai-video-3-0-pro/examples#example-telecommunications-documentary-title-sequence) · 8s: `$0.896` (~3m 22s)
- [reference-to-video](https://runware.ai/docs/models/klingai-video-3-0-pro/examples#example-rare-book-conservator-briefing): `$1.01` (~4m 46s)
- [multi-shot](https://runware.ai/docs/models/klingai-video-3-0-pro/examples#example-koji-culture-training-presenter-clip) · 1080p · 9s: `$1.51` (~3m 24s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

Provide at least one of `inputs.frameImages` and `inputs.referenceVideos`, or `width/height`, but not both.

---

Inside `inputs`, `frameImages` cannot be used with `referenceImages` or `referenceVideos`.

---

When `inputs.elements` is provided, provide exactly one of `inputs.frameImages` or both `inputs.referenceImages` and `inputs.referenceVideos`.

---

When `inputs.elements.frontalImage` or `inputs.elements.images` is provided, `inputs.elements.frontalImage` and `inputs.elements.images` are required.

---

When `inputs.elements.frontalImage` or `inputs.elements.images` or `inputs.elements.videos` is provided, `inputs.elements.description` is required.

---

When `inputs.frameImages` is provided, `inputs.elements` is limited to 3 items.

---

When `inputs.referenceImages` or `inputs.referenceVideos` or `providerSettings.klingai.characterOrientation` is provided, `inputs.referenceImages`, `inputs.referenceVideos`, and `providerSettings.klingai.characterOrientation` are required.

---

When `inputs.referenceVideos` is provided, `providerSettings.klingai.sound`, `providerSettings.klingai.multiPrompt`, `providerSettings.klingai.shotType`, and `duration` cannot be used.

---

When `inputs.referenceVideos` is not provided, provide exactly one of `positivePrompt` or `providerSettings.klingai.multiPrompt`.

---

When `inputs.referenceVideos` and `inputs.elements` are provided, `inputs.elements` is limited to 1 item and `providerSettings.klingai.characterOrientation` must be `video`.

---

`positivePrompt` cannot be used with `providerSettings.klingai.multiPrompt`.

---

Inside `providerSettings.klingai`, `shotType` cannot be used with `multiPrompt`.

---

When `providerSettings.klingai.keepOriginalSound` is provided, `inputs.referenceVideos` is required.

---

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `1080p (16:9)` | `1920x1080` |
| `1080p (1:1)` | `1440x1440` |
| `1080p (9:16)` | `1080x1920` |

## Notes

Kling 3.0 Pro supports multiple generation modes:

- **Text-to-Video:** Provide a prompt with `width`, `height`, and `duration`.
- **Image-to-Video:** Provide frame images via `inputs.frameImages` (up to 2, first/last). Dimensions are inherited from the image and cannot be set manually.
- **Motion Control:** Provide a reference video via `inputs.referenceVideos` (max 1). Optionally provide a reference image via `inputs.referenceImages` (max 1).

**Elements** allows you to include reusable assets like characters, objects, or voices in your video by referencing them in the prompt (e.g. `<<<element_1>>>`). On Kling 3.0, Elements is only available in Image-to-Video mode.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/klingai-video-3-0-pro#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/klingai-video-3-0-pro#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/klingai-video-3-0-pro#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/klingai-video-3-0-pro#request-outputformat)

- **Type**: `string`
- **Default**: `MP4`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP4\`: Widely supported video container (H.264), recommended for general use.
- \`WEBM\`: Optimized for web delivery.
- \`MOV\`: QuickTime format, common in professional workflows (Apple ecosystem).

**Allowed values**: `MP4` `WEBM` `MOV`

### [outputQuality](https://runware.ai/docs/models/klingai-video-3-0-pro#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/klingai-video-3-0-pro#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/klingai-video-3-0-pro#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/klingai-video-3-0-pro#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/klingai-video-3-0-pro#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/klingai-video-3-0-pro#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

#### [mode](https://runware.ai/docs/models/klingai-video-3-0-pro#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `fast`

Safety checking mode for video generation.

**Allowed values**:

- `fast` Checks key frames.
- `full` Checks all frames.

### [ttl](https://runware.ai/docs/models/klingai-video-3-0-pro#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/klingai-video-3-0-pro#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/klingai-video-3-0-pro#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [referenceImages](https://runware.ai/docs/models/klingai-video-3-0-pro#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `items: 1`

List of reference images (UUID, URL, Data URI, or Base64).

### [frameImages](https://runware.ai/docs/models/klingai-video-3-0-pro#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `2`
- **Size (each)**: `300 px or more`
- **Aspect ratio (each)**: `1:2.5 to 2.5:1`

An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target position in the video.

The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. Position can be specified using `frame` (named positions or frame indices) or `timestamp` (seconds), depending on model support. This is different from `referenceImages`, which provide overall visual guidance without constraining specific timeline positions.

When the `frame` parameter is omitted, automatic distribution rules apply:

- **1 image**: Used as the first frame.
- **2 images**: First and last frames.

**Examples**:

**Shorthand format:** When you don't need to specify a frame position, you can pass a plain image input directly.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]
```

**Object format:** When you need to specify a position, use an object with `image` and either `frame` or `timestamp` (model-dependent).

```json
"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  }
]
```

**First and last frames:** With two images, they automatically become the first and last frames of the video sequence. You can mix shorthand and object formats.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402",
  {
    "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe",
    "frame": "last"
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

Image input (UUID, URL, Data URI, or Base64).

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/klingai-video-3-0-pro#request-inputs-frameimages-format-2-image)

- **Path**: `inputs.frameImages.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

#### [frame](https://runware.ai/docs/models/klingai-video-3-0-pro#request-inputs-frameimages-format-2-frame)

- **Path**: `inputs.frameImages.frame`
- **Type**: `object`

Target frame position for the image. Supports first and last frame.

**Allowed values**:

- `first` First frame of the video.
- `last` Last frame of the video.
- `0` Frame index 0 (first frame).
- `-1` Frame index -1 (last frame).

### [referenceVideos](https://runware.ai/docs/models/klingai-video-3-0-pro#request-inputs-referencevideos)

- **Path**: `inputs.referenceVideos`
- **Type**: `array of strings`
- **Min items**: `items: 1`

List of reference videos (UUID or URL).

### [elements](https://runware.ai/docs/models/klingai-video-3-0-pro#request-inputs-elements)

- **Path**: `inputs.elements`
- **Type**: `array of objects (7 properties)`
- **Min items**: `1`
- **Max items**: `7`

Elements allow you to include reusable assets in your generation. Each element is identified by an `id` and can be referenced in the prompt using `<<<element_1>>>`, `<<<element_2>>>`, etc. in order of appearance.

An element can contain:

- **Images** via `frontalImage` plus `images` (1 to 3 additional angles).
- **Videos** via `videos`, on video models only (cannot be combined with images).
- **Voices** via `voices`, on video models only (can only be combined with images, not videos).

**Examples**:

**Create a new element with an image:**

```json
"positivePrompt": "<<<element_1>>> walking through a futuristic city",
"inputs": {
  "elements": [
    {
      "id": "my-character-id",
      "description": "A young woman with red hair",
      "frontalImage": "c64351d5-4c59-42f7-95e1-eace013eddab",
      "images": ["8f2a9c3e-1b4d-4e6f-a7c8-9d0e1f2a3b4c"],
      "tags": ["Character"]
    }
  ]
}
```

**Reuse a previously created element by ID:**

```json
"positivePrompt": "<<<element_1>>> sitting in a coffee shop, reading a book",
"inputs": {
  "elements": [
    {
      "id": "my-character-id"
    }
  ]
}
```

#### [id](https://runware.ai/docs/models/klingai-video-3-0-pro#request-inputs-elements-id)

- **Path**: `inputs.elements.id`
- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `20`

Unique identifier for this element. Use to create a new element or reference a previously created one.

#### [description](https://runware.ai/docs/models/klingai-video-3-0-pro#request-inputs-elements-description)

- **Path**: `inputs.elements.description`
- **Type**: `string`
- **Min**: `1`
- **Max**: `100`

Description of the element.

#### [frontalImage](https://runware.ai/docs/models/klingai-video-3-0-pro#request-inputs-elements-frontalimage)

- **Path**: `inputs.elements.frontalImage`
- **Type**: `string`

Frontal reference image for the element. Required when using image-based elements.

#### [images](https://runware.ai/docs/models/klingai-video-3-0-pro#request-inputs-elements-images)

- **Path**: `inputs.elements.images`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `3`

Reference images for the element. Up to 3 images. Requires frontalImage.

#### [videos](https://runware.ai/docs/models/klingai-video-3-0-pro#request-inputs-elements-videos)

- **Path**: `inputs.elements.videos`
- **Type**: `array of strings`
- **Min items**: `items: 1`

Reference video for the element. Cannot be combined with images or voices.

#### [voices](https://runware.ai/docs/models/klingai-video-3-0-pro#request-inputs-elements-voices)

- **Path**: `inputs.elements.voices`
- **Type**: `array of strings`
- **Min items**: `items: 1`

Voice audio for the element. Can only be combined with images, not videos.

#### [tags](https://runware.ai/docs/models/klingai-video-3-0-pro#request-inputs-elements-tags)

- **Path**: `inputs.elements.tags`
- **Type**: `array of strings`
- **Min items**: `1`

Classification tags for the element.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/klingai-video-3-0-pro#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `klingai:kling-video@3-pro`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/klingai-video-3-0-pro#request-positiveprompt)

- **Type**: `string`
- **Min**: `2`
- **Max**: `2500`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [negativePrompt](https://runware.ai/docs/models/klingai-video-3-0-pro#request-negativeprompt)

- **Type**: `string`
- **Min**: `2`
- **Max**: `2500`

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

**Learn more** (1 resource):

- [Prompts: Negative Prompts](https://runware.ai/docs/learn/prompts#negative-prompts) (learn)

### [width](https://runware.ai/docs/models/klingai-video-3-0-pro#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages and inputs.referenceVideos are not provided
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/klingai-video-3-0-pro#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages and inputs.referenceVideos are not provided
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [duration](https://runware.ai/docs/models/klingai-video-3-0-pro#request-duration)

- **Type**: `integer`
- **Min**: `3`
- **Max**: `15`
- **Step**: `1`
- **Default**: `5`

Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

**Provider Settings**

Parameters specific to this model provider. These must be nested inside the \`providerSettings.klingai\` object.

### [characterOrientation](https://runware.ai/docs/models/klingai-video-3-0-pro#request-providersettings-klingai-characterorientation)

- **Path**: `providerSettings.klingai.characterOrientation`
- **Type**: `string`

Source for character orientation reference.

**Allowed values**:

- `image` Match orientation from the reference image.
- `video` Match orientation from the reference video.

### [keepOriginalSound](https://runware.ai/docs/models/klingai-video-3-0-pro#request-providersettings-klingai-keeporiginalsound)

- **Path**: `providerSettings.klingai.keepOriginalSound`
- **Type**: `boolean`

Maintain the original sound from the reference video.

### [multiPrompt](https://runware.ai/docs/models/klingai-video-3-0-pro#request-providersettings-klingai-multiprompt)

- **Path**: `providerSettings.klingai.multiPrompt`
- **Type**: `array of objects (2 properties)`
- **Max items**: `6`

Sequential prompt segments for multi-shot generation. The sum of all segment durations must equal the root-level duration.

#### [prompt](https://runware.ai/docs/models/klingai-video-3-0-pro#request-providersettings-klingai-multiprompt-prompt)

- **Path**: `providerSettings.klingai.multiPrompt.prompt`
- **Type**: `string`
- **Required**: true
- **Min**: `3`
- **Max**: `512`

Text prompt describing the content for this segment.

#### [duration](https://runware.ai/docs/models/klingai-video-3-0-pro#request-providersettings-klingai-multiprompt-duration)

- **Path**: `providerSettings.klingai.multiPrompt.duration`
- **Type**: `integer`
- **Required**: true
- **Min**: `1`

Duration in seconds for this segment.

### [shotType](https://runware.ai/docs/models/klingai-video-3-0-pro#request-providersettings-klingai-shottype)

- **Path**: `providerSettings.klingai.shotType`
- **Type**: `string`
- **Value**: `intelligence`

Type of shot to generate.

### [sound](https://runware.ai/docs/models/klingai-video-3-0-pro#request-providersettings-klingai-sound)

- **Path**: `providerSettings.klingai.sound`
- **Type**: `boolean`

Enable native audio generation.

## Response Parameters

### [taskType](https://runware.ai/docs/models/klingai-video-3-0-pro#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/klingai-video-3-0-pro#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [videoUUID](https://runware.ai/docs/models/klingai-video-3-0-pro#response-videouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/klingai-video-3-0-pro#response-videourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/klingai-video-3-0-pro#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/klingai-video-3-0-pro#response-videodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output video.

### [NSFWContent](https://runware.ai/docs/models/klingai-video-3-0-pro#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/klingai-video-3-0-pro#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/klingai-video-3-0-pro/f99f458c-e3aa-4186-92d3-edb40e3d18b1.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "f9534830-ede7-430b-a015-d802b1a6e536",
  "model": "klingai:kling-video@3-pro",
  "positivePrompt": "Photorealistic product demonstration of a passive self-rising flood barrier installed across a modern warehouse loading-bay entrance. One continuous five-second shot from a low three-quarter cutaway angle clearly reveals the recessed mechanism beneath the concrete floor. Begin with the bright safety-yellow barrier lying flush with the ground as shallow storm water rushes toward it. The rising water enters the exposed chamber, lifts the internal buoyant float, and smoothly pivots the barrier upright. The rubber edge compresses firmly against the side seals, stopping the surge; water splashes dramatically against the deployed gate while the warehouse floor behind it remains completely dry. Precise believable mechanical motion, legible cause and effect, clean industrial design, cool gray concrete, saturated yellow hardware, deep blue-green water, crisp overcast lighting, polished engineering-film realism. Subtle camera push-in following the mechanism. Native environmental audio: approaching rainwater, accelerating rush and splashes, hollow chamber gurgle, mechanical hinge movement, decisive rubber-seal thump, water continuing to churn against the barrier. No narration, no music, no labels, no logos, no on-screen text.",
  "negativePrompt": "people, vehicles, branding, captions, diagrams, arrows, floating parts, impossible mechanics, water passing through the closed gate, wet floor behind barrier, shaky camera, distorted architecture",
  "width": 1920,
  "height": 1080,
  "duration": 5,
  "providerSettings": {
    "klingai": {
      "sound": true
    }
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/klingai-video-3-0-pro/5d219e7f-8968-481d-9e11-3410c7ac149d.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "b668226f-2445-4588-870e-f27e019f9aa3",
  "model": "klingai:kling-video@3-pro",
  "positivePrompt": "Continue directly and seamlessly from the supplied first frame as one polished six-second industrial product demonstration with no cuts. Preserve the exact machine, seed colors, tray, camera angle, lighting, and coral studio surface. The camera begins locked in the three-quarter overhead composition, then makes a very slow, precise push-in. The machine activates: its circular plate vibrates with controlled high-frequency motion, causing the tiny acid-yellow seeds to travel outward in orderly streams through the visible branching microchannels beneath the smoke-clear lid. Show the mechanism clearly and realistically—individual seeds separate rather than clump, advance one by one, and arrive at the outlet gates. In the final two seconds, the gates pulse sequentially and dispense exactly one seed into each visible propagation-tray cell while a slim physical indicator light on the housing progresses from amber to green. Emphasize stable product geometry, credible seed physics, smooth mechanical timing, sharp material detail, and an easy-to-understand workflow. Premium scientific-equipment art direction with bold ultramarine, coral, charcoal, and acid-yellow palette; bright, optimistic, precise mood. Native synchronized audio: soft electric startup tone, delicate vibration hum, faint seed ticks against clear channels, evenly timed gate clicks, and a subtle completion chime. No narration, captions, graphics, logos, labels, interface overlays, hands, or additional objects.",
  "duration": 6,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/9d792ede-80ea-4462-a9e8-92cee9b0c4c6.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

### first-last-frame (first-last-frame)

[Watch video](https://assets.runware.ai/examples/klingai-video-3-0-pro/ceabbf5b-bfe9-431f-b29a-d62e7e7a5b1a.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "524aa09a-a11c-489a-9e80-91f0dfb0232d",
  "model": "klingai:kling-video@3-pro",
  "positivePrompt": "Create an eight-second prestige documentary title sequence in one continuous, controlled shot, beginning exactly from the supplied first frame and resolving exactly into the supplied last frame. Hold briefly on the frontal 1940s telephone switchboard as indicator lamps wake one by one and the red patch cable gives a slight natural sway. The camera begins an extremely smooth pullback. Without a cut, the switchboard undergoes a tactile, believable transformation: circular jacks deepen into distant windows, brass dividers lengthen into avenues, tiny indicator bulbs become traffic and office lights, and the wooden cabinet recedes into the charcoal geometry of a contemporary city seen directly from above. Preserve the grid, central symmetry, and red loop throughout so every shape has a clear visual successor. The red cable gradually becomes a moving communications light trail, a pulse traveling around its curve and branching subtly through nearby streets. During the final two seconds, motion settles, haze drifts gently over the city, and the centered title already present in the destination frame resolves cleanly and remains stable: THE HUMAN LINE. Sophisticated archival-to-modern art direction; tobacco brown, aged ivory, oxblood red, charcoal, and restrained cyan; fine film grain, deep blacks, realistic materials, elegant pacing, no hard cuts, no frantic movement. Synchronized audio: low electrical room hum, tactile relay clicks accelerating into a muted urban night bed, one warm analog pulse traveling with the red line, then a restrained sub-bass resolve as the title settles; no speech and no music melody.",
  "negativePrompt": "Hard cuts, montage, unrelated imagery, warped grid, chaotic camera motion, zoom bursts, flicker, excessive neon, science-fiction interfaces, visible people, hands, logos, subtitles, extra lettering, misspelled title, unstable typography, cartoon rendering, glossy advertising style.",
  "duration": 8,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/1b4f8ff3-9035-49c6-b95d-2b3967d65c4d.jpg"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/338c25ac-5a26-4ee1-b4d6-45fbb351a230.jpg"
      }
    ]
  }
}
```

---

### reference-to-video (reference-to-video)

[Watch video](https://assets.runware.ai/examples/klingai-video-3-0-pro/944fac34-3978-493a-8f2c-fd6ece291392.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "51248efb-0741-4d83-9459-cd8f03941abf",
  "model": "klingai:kling-video@3-pro",
  "positivePrompt": "Create a polished internal museum training presenter clip in a rare-book quarantine laboratory. Preserve the exact identity and appearance of the woman in the reference image: her facial structure, warm brown complexion, short silver curls, tortoiseshell glasses, age, and dark plum conservation smock. Place her chest-up behind a stainless-steel examination bench, addressing the camera directly. Follow the reference video's straight-on orientation, timing, facial performance, restrained open-palm gesture, and concluding nod. Retain its original spoken dialogue and clean sound, with precise natural lip synchronization.\n\nThe background is a credible conservation workspace: a closed archival volume inside a transparent isolation tray, a compact HEPA unit, gray specimen cabinets, and an ultraviolet inspection lamp casting a subtle violet accent. Clinical but cinematic art direction with cool slate gray, ultraviolet violet, and small acid-chartreuse equipment details. Soft frontal key light, gentle violet edge light, realistic skin and fabric texture, shallow depth of field. Locked eye-level medium close-up with only a nearly imperceptible slow push-in. Calm, serious, procedural mood suitable for professional museum staff education. No captions, graphics, branding, labels, extra people, or camera cuts.",
  "providerSettings": {
    "klingai": {
      "characterOrientation": "video",
      "keepOriginalSound": true
    }
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/b3f53e42-75bf-435d-9f31-8ef88449ab69.jpg"
    ],
    "referenceVideos": [
      "https://assets.runware.ai/assets/inputs/c2fa03aa-d303-440d-8cb3-c4c85a903783.mp4"
    ]
  }
}
```

---

### elements (elements)

[Watch video](https://assets.runware.ai/examples/klingai-video-3-0-pro/9738a075-461a-4bf4-b5e5-5cf92dbfd6c2.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "8f2b63d6-d58a-458d-b9ed-b08e16ea797b",
  "model": "klingai:kling-video@3-pro",
  "positivePrompt": "Create a finished seven-second 16:9 performance segment for an art-pop single, opening exactly from the supplied first frame. Inside the drained retro municipal pool, <<<element_1>>> performs the lead vocal while <<<element_2>>> plays two chrome floor toms. Preserve both performers' faces, wardrobe, proportions, and colors from their element references throughout. Begin with the symmetrical floor-level wide shot: the vocalist snaps her head toward camera on the first beat as the percussionist strikes both drums, making the cobalt sleeve fringe flare naturally. The camera then glides rapidly down the center lane between them while they advance in synchronized angular steps. Reflections of chartreuse and cobalt ripple across pale aqua tiles as if cast by moving water, although the pool remains completely dry. Midway, transition through a clean overhead view: their choreography forms opposing geometric diagonals around the circular drums. Finish with a confident medium push-in on the vocalist delivering a brief original nonlexical hook while the percussionist lands one final visible strike behind her; stop on the impact with both performers sharply composed. Bold 1980s public-access performance styling elevated with contemporary cinematic polish, hard magenta window light, cyan edge lights, controlled haze, crisp skin detail, subtle 35mm grain, punchy contrast, energetic editorial pacing, believable body mechanics, stable instruments and architecture. Generate synchronized original audio: dry 118 BPM industrial art-pop with gated floor toms, clipped analog bass, handclaps, a short wordless female vocal hook, tiled-room reverb, and drum impacts precisely aligned to the visible mallet strikes. No titles, captions, logos, audience, water, costume changes, extra performers, or malformed instruments.",
  "negativePrompt": "Unstable faces, identity changes, duplicated people, extra limbs, malformed hands, floating drumsticks, warped drums, wet pool, water, crowd, text, subtitles, logos, flicker, jitter, smeared motion, cartoon rendering, low-detail faces, asynchronous percussion.",
  "duration": 7,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/558a9600-fac1-401f-bab2-719cdb1dfacb.jpg",
        "frame": "first"
      }
    ],
    "elements": [
      {
        "id": "mara_vocal",
        "description": "Lead art-pop vocalist in a chartreuse tailored suit with a blunt black bob.",
        "frontalImage": "https://assets.runware.ai/assets/inputs/08820d89-1c18-4612-a2ae-a131f3391711.jpg",
        "images": [
          "https://assets.runware.ai/assets/inputs/372a7189-5de6-4ddd-bc5a-31ae8a4d1958.jpg"
        ],
        "tags": [
          "Character"
        ]
      },
      {
        "id": "iko_drummer",
        "description": "Tall percussionist in a cobalt fringed boiler suit carrying white felt mallets.",
        "frontalImage": "https://assets.runware.ai/assets/inputs/a1d211f4-32cd-4cbc-8f86-4a0668a6ddcd.jpg",
        "images": [
          "https://assets.runware.ai/assets/inputs/62098343-e4f4-4a3d-a026-377936dd6d4c.jpg"
        ],
        "tags": [
          "Character"
        ]
      }
    ]
  }
}
```

---

### multi-shot (multi-shot)

[Watch video](https://assets.runware.ai/examples/klingai-video-3-0-pro/d56a3649-f52c-4368-a909-511b61542de2.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "39a39beb-8d92-46ae-9d62-055613231a6a",
  "model": "klingai:kling-video@3-pro",
  "width": 1080,
  "height": 1920,
  "duration": 9,
  "providerSettings": {
    "klingai": {
      "sound": true,
      "multiPrompt": [
        {
          "prompt": "Wide establishing shot introducing the main subject in its environment.",
          "duration": 3
        },
        {
          "prompt": "The main subject performs a clear action as the camera moves closer.",
          "duration": 3
        },
        {
          "prompt": "A concluding shot resolves the action with a strong final composition.",
          "duration": 3
        }
      ]
    }
  }
}
```