> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Kling 3.0 Turbo

> Text-to-video and image-to-video with synchronized native audio, at 720p or 1080p for 3 to 15 seconds, with aspect ratio and prompt control.

![Kling 3.0 Turbo](https://media.empiriolabs.ai/model-logos/kling-3-0-turbo.png)

[Kling AI](/providers/kling) · Video Generation

`POST /v1/videos/generations`

Text-to-video and image-to-video with synchronized native audio, at 720p or 1080p for 3 to 15 seconds, with aspect ratio and prompt control.

## At a glance

| Field               | Value                                                  |
| ------------------- | ------------------------------------------------------ |
| Model id            | `kling-3-0-turbo`                                      |
| Model release date  | 2026-06-17                                             |
| Input modalities    | Text, Image                                            |
| Output modalities   | Video                                                  |
| Context window      | -                                                      |
| Weight precision    | -                                                      |
| Features            | text_to_video, image_to_video, audio, video_generation |
| Native inference    | No                                                     |
| New                 | No                                                     |
| Supported endpoints | `POST /v1/videos/generations`                          |
| Alternate model ids | `kling-3.0-turbo`, `kling/kling-3-0-turbo`             |

## Pricing

| Charge | Spec       | Rate    |
| ------ | ---------- | ------- |
| 720p   | per second | \$0.18  |
| 1080p  | per second | \$0.225 |

## Example request

```bash
curl https://api.empiriolabs.ai/v1/videos/generations \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "kling-3-0-turbo", "prompt": "sunrise over the ocean", "duration": 6}'
```

## Parameters

| Parameter      | Type    | Required | Default  | Description                                                                                                                   |
| -------------- | ------- | -------- | -------- | ----------------------------------------------------------------------------------------------------------------------------- |
| `prompt`       | string  | yes      | -        | Describe the video (text-to-video) or the motion to apply to the source image (image-to-video).                               |
| `image`        | string  | no       | -        | Optional source image (URL or base64). When provided, the request is image-to-video; when omitted, text-to-video.             |
| `resolution`   | enum    | no       | `"720p"` | Output resolution. 720p renders faster; 1080p is higher fidelity. · Allowed: `720p`, `1080p`                                  |
| `aspect_ratio` | enum    | no       | `"16:9"` | Aspect ratio of the output. Used for text-to-video; image-to-video follows the source image. · Allowed: `16:9`, `9:16`, `1:1` |
| `duration`     | number  | no       | `5`      | Video length in seconds. · Range: 3 – 15                                                                                      |
| `watermark`    | boolean | no       | false    | Add a watermark to the generated video. Off by default.                                                                       |

## Notes

Text-to-video and image-to-video with synchronized native audio, up to 1080p. Workflow auto-detected: a prompt alone is text-to-video, adding a source image is image-to-video.

**Prompting**

* There is no separate negative prompt. To steer away from unwanted elements, describe them in your prompt, for example: "a calm forest at dawn, avoid blurry motion, no on-screen text".

**Multi-shot**

* Generate up to 6 sequential shots by formatting the prompt like this (shot durations must sum to the total duration):

```
shot 1, <seconds>, <description>; shot 2, <seconds>, <description>;
```

**Input limits**

* Prompt up to 3,072 characters. Resolution 720p or 1080p. Duration 3 to 15 seconds. Aspect ratio 16:9, 9:16, or 1:1 for text-to-video (image-to-video follows the source image).
* Image inputs: JPEG or PNG, at least 300px per side, aspect within 1:2.5 to 2.5:1, up to 50 MB.

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/kling-3-0-turbo`.