Skip to main content
← Kling 3.0 Endpoint: POST https://api.higgsfield.ai/kling-video/v3.0/std/text-to-video Endpoint ID: kling-video/v3.0/std/text-to-video ▶Open API PlaygroundKling 3.0 · Standard · Text to video↗

Usage notes

  • Always include a non-empty top-level prompt, including when using multi_prompt. Keep it within 2,500 characters; longer prompts are truncated.
  • For custom shots, set multi_shots to true and provide 1–6 multi_prompt objects. Each object needs prompt (at most 512 characters) and duration (a positive integer from 1 to 15 seconds).
  • Custom-shot durations are summed for generation and billing; the top-level duration does not override that sum. With multi_shots enabled and no custom shots, the top-level duration is retained.
  • Native audio uses sound: on or off and defaults to on.
  • elements contains Kling element IDs as decimal strings. Each ID must belong to the account making the request; arbitrary provider IDs are rejected.

Quick start

Input schema

string
default:"on"
Enable sound for the output video. Allowed values: "on", "off".
string
Write your prompt here
integer
default:"5"
Requested output duration in seconds. Minimum: 3. Maximum: 15.
array
Each item: string.
number
default:"0.5"
Minimum: 0. Maximum: 1. Multiple of: 0.01.
boolean
default:"false"
See the complete JSON schema below.
string
default:"16:9"
Output width-to-height ratio. Allowed values: "16:9", "9:16", "1:1".
array
Minimum items: 1. Maximum items: 6.

Response

Submission returns a request handle. Poll status_url until status is completed, or use webhooks.
Accepted
A completed response includes the following output fields:
See idempotent requests, polling, request errors and authentication for shared request handling.