Skip to main content
Endpoint: POST https://api.higgsfield.ai/kling-video/v3.0/4k/text-to-video Endpoint ID: kling-video/v3.0/4k/text-to-video Try Kling 3.0 4K Text to VideoOpen the model in the Higgsfield Playground with your own inputs.

Quick Start

Input Schema

string
default:"on"
Enable or disable generated sound. Supported values: on, off.
string
Provide a prompt describing the desired output, as shown in the examples. Kling uses up to the first 2,500 characters.
integer
default:"5"
Output duration in seconds. Supported range: 315.
array
Reusable Kling element IDs. Each item must be a string.
number
default:"0.5"
How strongly the generation follows the prompt. Supported range: 01 in increments of 0.01.
boolean
default:"false"
Enable a multi-shot sequence.
string
default:"16:9"
Output aspect ratio. Supported values: 16:9, 9:16, 1:1.
array
Ordered shot definitions used when multi_shots is true. Accepts up to 6 objects; for each shot, provide prompt (up to 512 characters) and duration (115 seconds).

Output Schema

string
required
Request state. A newly accepted request returns queued.
string
required
Stable identifier used for polling, cancellation, and support.
string
required
URL to poll until the request reaches a terminal state.
string
required
URL used to cancel a request before processing starts.
object
Completed video output containing its download url.

Input Example

Output Example

Use an SDK for automatic polling, or poll the returned status URL.