Skip to main content
POST
/
kling
/
v1
/
videos
/
text2video
Text to Video
curl --request POST \
  --url https://api.cometapi.com/kling/v1/videos/text2video \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "A happy scene of a vacation on the beach."
}
'
{
  "code": 123,
  "message": "<string>",
  "request_id": "<string>",
  "data": {
    "task_id": "<string>",
    "task_status": "<string>",
    "created_at": 123,
    "updated_at": 123
  }
}
Use this endpoint to create a Kling text-to-video task from a prompt. It starts an async job rather than returning a finished video immediately.

​
First working request

  • Send a short prompt first
  • Add aspect_ratio, duration, or mode only after the basic flow works
  • Set callback_url if you want push delivery instead of pure polling

​
Task flow

1

Submit the generation request

Create the task through this endpoint and save the returned Kling task id.
2

Poll the task state

Check progress through Individual Queries until the task reaches a terminal state.
3

Persist the result

Once Kling returns the finished asset metadata, move the result into your own storage if you need long retention.
For the full parameter matrix and model-track details, refer to the official Kling documentation. Use the request and response shapes on this page as the CometAPI wrapper reference.

Authorizations

​
Authorization
string
header
required

Bearer token authentication. Use your CometAPI key.

Headers

​
Content-Type
string

Must be application/json.

Body

application/json
​
prompt
string
default:Hello
required

Text prompt describing the video to generate. Maximum 500 characters.

​
negative_prompt
string

Elements to exclude from the video. Maximum 200 characters.

​
aspect_ratio
string

Output aspect ratio (width:height). Options: 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3.

​
callback_url
string

Webhook URL to receive task status updates when the task completes.

​
model_name
string

Kling model variant to use. See the Models page for current options.

​
cfg_scale
number

Prompt adherence strength. Higher values follow the prompt more closely. Range: 0–1.

​
mode
enum<string>

Generation mode. std for standard (faster), pro for professional (higher quality).

Available options:
std,
pro
​
duration
string

Output video length in seconds. Options: 5, 10.

​
camera_control
object

Camera motion preset or manual configuration. Omit for automatic camera movement.

​
external_task_id
string

Custom task id for your own tracking. Does not replace the system-generated task id but can be used to query tasks. Must be unique per user.

Response

200 - application/json

Successful Response

​
code
integer

Error code; specifically define the error code

​
message
string

error message

​
request_id
string

Request ID, system-generated, for tracking requests, troubleshooting issues

​
data
object