Skip to main content
POST
cURL
Send a prompt to POST /text-to-video/{model} to create a video task. The response contains an id that you use to retrieve the result.

Choose a model

Put the model ID in the URL. Do not add a model field to the JSON body.

Request parameters

The following request creates a five-second, single-shot video:
Send this body to https://api.cometapi.com/text-to-video/kling-3.0-turbo with your CometAPI API key. The OpenAPI code panel provides Shell, Python, and JavaScript requests with the same body.

Retrieve the video

The create response has this shape:
Save data.id. Use Get a Kling task with that ID until the task reaches a terminal status. Read the video URL from the task’s outputs array.

Authorizations

Authorization
string
header
required

Authenticate with your CometAPI API key.

Path Parameters

model
enum<string>
default:kling-3.0-turbo
required

Kling model ID. kling-3.0 supports 4k resolution. The 2.x models accept 5- or 10-second duration.

Available options:
kling-3.0-turbo,
kling-3.0,
kling-2.6,
kling-2.5-turbo

Body

application/json
prompt
string
required

Text description of the video to generate.

Minimum string length: 1
settings
object

Video generation settings. The model ID determines which resolution, duration, and audio values are accepted.

options
object

Optional task delivery and tracking settings.

Response

200 - application/json

The task was created. Use data.id to retrieve its status and video output.

code
required

Request result code. 0 or success indicates acceptance.

message
string
required

Result message.

data
object
required

Task identifier and submission status.

msg
string

Additional result message when included in the response.

Last modified on September 25, 2026