Kling 3.0 Standard Image-to-Video Serverless API

Transform starting images into cinematic 1080p videos with controlled motion and optional audio.

~155.31s
$0.504 - $8.40 per generation
PlaygroundAPI
Pricing
 1import requests
 2import json
 3
 4url = "https://api.segmind.com/v1/kling-3-standard-image2video"
 5headers = {
 6    "x-api-key": "YOUR_API_KEY",
 7    "Content-Type": "application/json"
 8}
 9
10data = {
11    "prompt": "The subject moves naturally with realistic physics and smooth camera motion.",
12    "duration": "5",
13    "cfg_scale": 0.5,
14    "aspect_ratio": "16:9",
15    "generate_audio": true,
16    "negative_prompt": "blur, distort, and low quality",
17    "start_image_url": ""
18}
19
20response = requests.post(url, headers=headers, json=data)
21
22if response.status_code == 200:
23    result = response.json()
24    print(json.dumps(result, indent=2))
25else:
26    print(f"Error: {response.status_code}")
27    print(response.text)

API Endpoint

POSThttps://api.segmind.com/v1/kling-3-standard-image2video

Parameters

promptrequired
string

Describe the motion and animation to create from the image.

start_image_urlrequired
string (uri)

Starting image to animate. This will be the first frame. Max 50MB.

aspect_ratiooptional
string

Aspect ratio of the generated video.

Default: "16:9"
Allowed values :
"16:9""9:16""1:1"
cfg_scaleoptional
number

Prompt adherence strength.

Default: 0.5Range: 0 - 1
durationoptional
string

Length of the output video in seconds.

Default: "5"
Allowed values (13 total):
"3""4""5""6""7""8""9""10""11""12"+3 more
elementsoptional
object[]

Character/object elements to include. Reference in prompt with @Element1, @Element2. Max 3 elements.

Array items:
frontal_image_urloptional
string (uri)

Frontal view image of the character or object.

reference_image_urlsoptional
string[]

Up to 3 reference images for this element.

end_image_urloptional
string (uri)

Ending image. Animation transitions from start to end. Max 50MB.

generate_audiooptional
boolean

Generate synchronized audio. Supports Chinese and English.

Default: true
multi_promptoptional
object[]

Multi-shot video generation. Each segment has its own prompt and duration. Max 5 segments.

Array items:
promptrequired
string

Prompt for this video segment. Max 512 characters.

durationoptional
string

Duration for this segment in seconds.

Default: "5"
negative_promptoptional
string

Specify elements to avoid.

Default: "blur, distort, and low quality"
shot_typeoptional
string

Camera shot type.

Default: "customize"
voice_idsoptional
string[]

Voice IDs for audio. Reference in prompt as <<<voice_1>>>, <<<voice_2>>>. Max 2. Get voice IDs from the Kling Create Voice endpoint: https://www.segmind.com/models/kling-create-voice

Response Type

Returns: Video

Common Error Codes

The API returns standard HTTP status codes. Detailed error messages are provided in the response body.

400

Bad Request

Invalid parameters or request format

401

Unauthorized

Missing or invalid API key

403

Forbidden

Insufficient permissions

404

Not Found

Model or endpoint not found

406

Insufficient Credits

Not enough credits to process request

429

Rate Limited

Too many requests

500

Server Error

Internal server error

502

Bad Gateway

Service temporarily unavailable

504

Timeout

Request timed out