Skip to main content
POST
/
kling
/
v1
/
videos
/
omni-video
cURL
curl https://api.cometapi.com/kling/v1/videos/omni-video \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
      "model_name": "kling-v3-omni",
      "prompt": "A paper boat drifts across a calm pond at sunrise",
      "mode": "pro",
      "aspect_ratio": "16:9",
      "duration": "5",
      "sound": "off"
    }'
{
  "code": 0,
  "message": "SUCCEED",
  "data": {
    "task_id": "<task_id>",
    "task_status": "submitted",
    "task_info": {
      "external_task_id": null
    },
    "task_status_msg": null,
    "created_at": 1773366840306,
    "updated_at": 1773366840306
  }
}
Use this endpoint for the O1-compatible Kling Omni workflow exposed by CometAPI, including plain text-to-video, image-referenced generation, and video transformation flows.
For the complete provider parameter reference, see the Kling Omni Video documentation.

​
Choose the input mode

  • Text-to-video: send prompt, mode, aspect_ratio, and duration
  • Image-referenced generation: add image_list items with image_url and type such as first_frame
  • Element-guided generation: add element_list items with element_id
  • Video transformation: add video_list items with video_url, refer_type, and optional keep_original_sound set to yes or no
  • Multi-shot generation: set multi_shot: true, choose shot_type, and send either prompt or multi_prompt
  • Keep model_name as kling-video-o1 or kling-v3-omni, or omit it to use the route default

​
Duration and aspect ratio

SettingSupported valuesDefaultBoundary behavior
duration for text or first-frame video"5", "10""5"Send the value as a string and use one of the two fixed generation lengths.
duration with reference video inputinput video length from 3 to 10 secondsinput lengthThe generated duration follows the base video and ignores the request value.
aspect_ratio16:9, 9:16, 1:116:9Required when no first-frame image or base video controls the frame.
modestd, propropro is the default for Omni Video.
Kling Omni does not expose an exact size field. Treat aspect_ratio as a frame-shape request; a 16:9 text-to-video request can render as full-HD 1920x1080.

​
Task flow

1

Create the Omni task

Submit the request and store the returned task_id.
2

Poll the Omni task

Continue with Get a Kling Omni video until the task finishes.
3

Persist the finished video

Move the returned MP4 URL into your own storage if you need durable access.

Authorizations

​
Authorization
string
header
required

Bearer token authentication. Use your CometAPI key.

Headers

​
Content-Type
string

Content type of the request body.

Body

application/json
​
prompt
string
required

Text prompt describing the desired video. Max 2500 characters. Reference images or elements inline using <<<image_1>>>, <<<element_1>>>, <<<video_1>>> syntax.

​
model_name
enum<string>
default:kling-video-o1

Omni Video model. Omit to use kling-video-o1.

Available options:
kling-video-o1,
kling-v3-omni
​
multi_shot
boolean
default:false

Whether to generate a multi-shot video. When true, use shot_type and either prompt or multi_prompt according to the selected storyboard method.

​
shot_type
enum<string>

Storyboard method for multi-shot generation. Required when multi_shot is true.

Available options:
customize,
intelligence
​
multi_prompt
object[]

Storyboard prompts for multi_shot: true with shot_type: customize. Supports 1 to 6 storyboard items; item durations should add up to the requested total duration.

Required array length: 1 - 6 elements
​
image_list
object[]

Optional image references for image-referenced Omni generation.

​
element_list
object[]

Optional element references for element-guided Omni generation.

​
video_list
object[]

Optional video references for video transformation workflows.

​
sound
enum<string>
default:off

Whether to generate audio with the video. Use on or off; when video_list is present, use off.

Available options:
on,
off
​
mode
enum<string>
default:pro

Generation mode. std (standard, faster and more cost-effective) or pro (professional, higher quality output). The default is pro.

Available options:
std,
pro
​
aspect_ratio
enum<string>

Aspect ratio request for beta Kling Omni generation. The endpoint does not expose an exact size field; a 16:9 text-to-video request can render as 1920x1080.

Available options:
16:9,
9:16,
1:1
​
duration
enum<string>
default:5

Requested output length. Use 5 or 10 as a string for text, image, and first-frame workflows; base-video workflows follow the source video length.

Available options:
3,
4,
5,
6,
7,
8,
9,
10,
11,
12,
13,
14,
15
​
watermark_info
object

Watermark options. When enabled is true, the task can return watermarked result URLs in addition to original result URLs.

​
callback_url
string<uri>

Webhook URL for task status notifications. The server sends a callback when the task status changes.

​
external_task_id
string

Optional user-defined task ID for your own tracking. Does not replace the system-generated task ID. Must be unique per account.

Response

200 - application/json

Success

​
code
integer
required

Response code. 0 means the task request was accepted.

​
message
string
required

Response message.

​
data
object
required
​
request_id
string

Request identifier returned by CometAPI when present.