> ## Documentation Index
> Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Create a Kling Omni video
> Use CometAPI POST /kling/v1/videos/omni-video to create Kling O1 video tasks and track status with the Omni query route.
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](https://kling.ai/document-api/api/video/o1/video-omni).
## 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
| Setting | Supported values | Default | Boundary 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 input | input video length from `3` to `10` seconds | input length | The generated duration follows the base video and ignores the request value. |
| `aspect_ratio` | `16:9`, `9:16`, `1:1` | `16:9` | Required when no first-frame image or base video controls the frame. |
| `mode` | `std`, `pro` | `pro` | `pro` 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
Submit the request and store the returned `task_id`.
Continue with [Get a Kling Omni video](./omni-query) until the task finishes.
Move the returned MP4 URL into your own storage if you need durable access.
## OpenAPI
````yaml api/openapi/video/kling/post-omni-video.openapi.json POST /kling/v1/videos/omni-video
openapi: 3.1.0
info:
title: Omni Video API (Beta)
version: 1.0.0
servers:
- url: https://api.cometapi.com
security:
- bearerAuth: []
paths:
/kling/v1/videos/omni-video:
post:
summary: Omni Video (Beta)
operationId: omni_video
parameters:
- name: Content-Type
in: header
required: false
description: Content type of the request body.
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- prompt
properties:
model_name:
type: string
description: Omni Video model. Omit to use `kling-video-o1`.
default: kling-video-o1
enum:
- kling-video-o1
- kling-v3-omni
multi_shot:
type: boolean
description: >-
Whether to generate a multi-shot video. When `true`, use
`shot_type` and either `prompt` or `multi_prompt` according
to the selected storyboard method.
default: false
shot_type:
type: string
description: >-
Storyboard method for multi-shot generation. Required when
`multi_shot` is `true`.
enum:
- customize
- intelligence
prompt:
type: string
description: >-
Text prompt describing the desired video. Max 2500
characters. Reference images or elements inline using
`<<>>`, `<<>>`, `<<>>` syntax.
multi_prompt:
type: array
description: >-
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.
minItems: 1
maxItems: 6
items:
type: object
required:
- index
- prompt
- duration
properties:
index:
type: integer
description: Storyboard sequence number.
prompt:
type: string
description: >-
Prompt for this storyboard item. Maximum 512
characters.
duration:
type: string
description: Duration in seconds for this storyboard item.
additionalProperties: false
image_list:
type: array
description: >-
Optional image references for image-referenced Omni
generation.
items:
type: object
properties:
image_url:
type: string
description: Image URL or base64 image string.
type:
type: string
description: >-
Frame role for the image. Use `first_frame` for a
starting frame or `end_frame` for an ending frame.
enum:
- first_frame
- end_frame
element_list:
type: array
description: >-
Optional element references for element-guided Omni
generation.
items:
type: object
properties:
element_id:
type: string
description: >-
Element id referenced from the prompt, such as
`<<>>`.
video_list:
type: array
description: >-
Optional video references for video transformation
workflows.
items:
type: object
properties:
video_url:
type: string
description: Video URL for the reference clip.
refer_type:
type: string
description: Reference role, such as `base`.
keep_original_sound:
type: string
description: >-
Whether to keep the original audio from the reference
video. Use `yes` or `no`.
enum:
- 'yes'
- 'no'
sound:
type: string
description: >-
Whether to generate audio with the video. Use `on` or `off`;
when `video_list` is present, use `off`.
enum:
- 'on'
- 'off'
default: 'off'
mode:
type: string
description: >-
Generation mode. `std` (standard, faster and more
cost-effective) or `pro` (professional, higher quality
output). The default is `pro`.
enum:
- std
- pro
default: pro
aspect_ratio:
type: string
description: >-
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.
enum:
- '16:9'
- '9:16'
- '1:1'
duration:
type: string
description: >-
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.
default: '5'
enum:
- '3'
- '4'
- '5'
- '6'
- '7'
- '8'
- '9'
- '10'
- '11'
- '12'
- '13'
- '14'
- '15'
watermark_info:
type: object
description: >-
Watermark options. When `enabled` is `true`, the task can
return watermarked result URLs in addition to original
result URLs.
properties:
enabled:
type: boolean
description: Whether to request watermarked result URLs.
additionalProperties: false
callback_url:
type: string
description: >-
Webhook URL for task status notifications. The server sends
a callback when the task status changes.
format: uri
external_task_id:
type: string
description: >-
Optional user-defined task ID for your own tracking. Does
not replace the system-generated task ID. Must be unique per
account.
default:
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'
examples:
Default:
summary: Kling V3 Omni video request
value:
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'
responses:
'200':
description: Success
content:
application/json:
schema:
type: object
required:
- code
- message
- data
properties:
code:
type: integer
description: Response code. `0` means the task request was accepted.
message:
type: string
description: Response message.
request_id:
type: string
description: Request identifier returned by CometAPI when present.
data:
type: object
required:
- task_id
- task_status
- task_info
- created_at
- updated_at
properties:
task_id:
type: string
description: Task ID generated by the system.
task_status:
type: string
description: Task status.
enum:
- submitted
- processing
- succeed
- failed
task_info:
type: object
description: >-
Task metadata, including `external_task_id` when
supplied.
properties:
external_task_id:
type:
- string
- 'null'
additionalProperties: true
task_status_msg:
type:
- string
- 'null'
description: Status details when present.
created_at:
type: integer
description: >-
Task creation time as a Unix timestamp in
milliseconds.
updated_at:
type: integer
description: Task update time as a Unix timestamp in milliseconds.
additionalProperties: true
additionalProperties: true
example:
code: 0
message: SUCCEED
data:
task_id:
task_status: submitted
task_info:
external_task_id: null
task_status_msg: null
created_at: 1773366840306
updated_at: 1773366840306
x-codeSamples:
- lang: Shell
label: Default
source: |
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"
}'
- lang: Python
label: Default
source: |
import os
import requests
response = requests.post(
"https://api.cometapi.com/kling/v1/videos/omni-video",
headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]},
json={
"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"
},
)
result = response.json()
print(result.get("code"), result.get("data", {}).get("task_id"))
- lang: JavaScript
label: Default
source: >
const response = await
fetch("https://api.cometapi.com/kling/v1/videos/omni-video", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.COMETAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"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"
}),
});
const result = await response.json();
console.log(result.code, result.data?.task_id);
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: Bearer token authentication. Use your CometAPI key.
````