Skip to main content
POST
/
v1
/
ai
/
video
/
kling-v3-std
Kling 3 Standard - Generate video
curl --request POST \
  --url https://api.freepik.com/v1/ai/video/kling-v3-std \
  --header 'Content-Type: application/json' \
  --header 'x-freepik-api-key: <api-key>' \
  --data '
{
  "webhook_url": "<string>",
  "prompt": "<string>",
  "multi_prompt": [
    {
      "prompt": "<string>",
      "duration": "3"
    }
  ],
  "start_image_url": "<string>",
  "end_image_url": "<string>",
  "elements": [
    {
      "reference_image_urls": [
        "<string>"
      ],
      "frontal_image_url": "<string>"
    }
  ],
  "generate_audio": true,
  "multi_shot": false,
  "shot_type": "customize",
  "aspect_ratio": "16:9",
  "duration": "5",
  "negative_prompt": "blur, distort, and low quality",
  "cfg_scale": 0.5
}
'
"<unknown>"

Authorizations

​
x-freepik-api-key
string
header
required

Your Freepik API key. Required for authentication. Learn how to obtain an API key

Body

application/json
​
webhook_url
string<uri>

Optional callback URL that receives asynchronous notifications when the task changes status. The payload includes the task status and result URL when completed.

​
prompt
string

Text prompt describing the desired video content. Maximum 2500 characters. Required for text-to-video mode or when not using multi_prompt.

Tips for better results:

  • Be specific about motion, camera angles, and actions
  • Describe the scene, characters, and atmosphere
  • Reference elements in your prompt as @Element1, @Element2
  • Reference voices with <<<voice_1>>> and <<<voice_2>>>
Maximum string length: 2500
​
multi_prompt
object[]

Multi-shot prompts with durations for sequential video generation. Each item specifies a prompt and duration (in seconds) for that shot. Maximum 6 shots. Total duration across all shots cannot exceed 15 seconds.

Only effective when shot_type is set. When multi_prompt is provided without an explicit shot_type, it defaults to "customize". When shot_type is "intelligent", Kling can auto-segment the video even without multi_prompt.

Maximum array length: 6
​
start_image_url
string

URL of the image to use as the first frame of the video. Required for image-to-video mode.

Image requirements:

  • Minimum: 300x300 pixels
  • Maximum: 10MB file size
  • Aspect ratio: 1:2.5 to 2.5:1
  • Formats: JPG, JPEG, PNG
​
end_image_url
string

URL of the image to use as the final frame of the video. Optional for image-to-video mode.

Image requirements:

  • Same as start_image_url
​
elements
object[]

Custom characters/objects with reference images for consistent identity across the video. Reference in your prompt as @Element1, @Element2, etc. When elements are provided, the request is processed in image-to-video mode. For best results, also provide a start_image_url.

​
generate_audio
boolean
default:true

Whether to generate native audio for the video.

​
multi_shot
boolean
default:false

Enable multi-shot mode for multi-scene video generation. When true, use shot_type and multi_prompt to define scenes. When false (default), generates a single continuous video.

​
shot_type
enum<string>
default:customize

Controls how multi-shot video generation is segmented:

  • customize: User provides explicit per-shot prompts and durations via the multi_prompt array. Each shot is defined manually.
  • intelligent: Enables automatic scene segmentation by Kling AI. Can be used without multi_prompt (Kling auto-segments the video based on the main prompt) or with multi_prompt (user-defined shots combined with AI segmentation).

Note: This parameter maps to Kling's internal "intelligence" spelling for the intelligent option. Defaults to "customize" when multi_prompt is provided.

Available options:
customize,
intelligent
​
aspect_ratio
enum<string>
default:16:9

Aspect ratio for the generated video:

  • 16:9: Landscape (widescreen) - ideal for YouTube, presentations
  • 9:16: Portrait (vertical) - ideal for TikTok, Instagram Stories, Reels
  • 1:1: Square - ideal for Instagram posts, social media
Available options:
16:9,
9:16,
1:1
​
duration
enum<string>
default:5

Duration of the generated video in seconds.

Range: 3-15 seconds Note: When using multi-shot mode, total duration across all shots cannot exceed 15 seconds.

Available options:
3,
4,
5,
6,
7,
8,
9,
10,
11,
12,
13,
14,
15
​
negative_prompt
string
default:blur, distort, and low quality

Undesired elements to avoid in the generated video. Maximum 2500 characters.

Maximum string length: 2500
​
cfg_scale
number<float>
default:0.5

Guidance scale controlling prompt adherence versus creative freedom. Range: 0 to 1. Values above 1 are not supported for Kling 3 (only Kling 1.x models support cfg_scale up to 2).

  • 0: Maximum creative freedom, loosest interpretation of the prompt
  • 0.5 (default): Balanced between prompt adherence and creativity
  • 1: Strongest adherence to the prompt, least creative variation
Required range: 0 <= x <= 1

Response

OK - Task created successfully

OK - The task exists and the status is returned