> ## 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.
# Ein Kling Omni-Video erstellen
> Verwenden Sie CometAPI POST /kling/v1/videos/omni-video, um Kling O1-Videotasks zu erstellen und den Status mit der Omni-Abfrageroute nachzuverfolgen.
Verwenden Sie diesen Endpoint für den O1-kompatiblen Kling Omni-Workflow, der über CometAPI bereitgestellt wird, einschließlich Text-zu-Video und Generation mit Referenz auf ein Bild des ersten Frames.
Die vollständige Referenz der Anbieterparameter finden Sie in der [Kling Omni Video-Dokumentation](https://kling.ai/document-api/api/video/o1/video-omni).
## Eingabemodus wählen
* Text-zu-Video: Senden Sie `prompt`, `mode`, `aspect_ratio` und `duration`
* Referenzbild für den ersten Frame: Fügen Sie `image_list`-Elemente mit `image_url` und `type: first_frame` hinzu und referenzieren Sie dann das Bild in `prompt` als `<<>>`
* Ausgabe mit Wasserzeichen: Fügen Sie `watermark_info.enabled: true` hinzu, wenn Sie in der Abfrageantwort eine Video-URL mit Wasserzeichen benötigen
* Model ID: Lassen Sie `model_name` weg, um den Standardwert der Route zu verwenden, oder senden Sie eine getestete Omni Video-Model ID wie `kling-video-o1` oder `kling-v3-omni`
## Dauer und Seitenverhältnis
| Einstellung | Unterstützte Werte | Standard | Grenzverhalten |
| ------------------------------------------- | --------------------- | -------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
| `duration` für Text- oder First-Frame-Video | `"5"`, `"10"` | `"5"` | Senden Sie den Wert als String und verwenden Sie eine der beiden festen Generierungslängen. |
| `aspect_ratio` | `16:9`, `9:16`, `1:1` | `16:9` | Erforderlich, wenn kein Bild des ersten Frames den Frame steuert. |
| `mode` | `std`, `pro` | Routenstandard | Senden Sie `std` für die Standardgenerierung oder `pro` nur dann, wenn Ihr ausgewähltes Modell den Modus mit höherer Qualität unterstützt. |
Kling Omni stellt kein exaktes Feld `size` bereit. Behandeln Sie `aspect_ratio` als Anfrage für die Frame-Form; eine Text-zu-Video-Anfrage mit `16:9` kann als Full-HD `1920x1080` gerendert werden.
## Task-Ablauf
Senden Sie die Anfrage und speichern Sie das zurückgegebene `task_id`.
Fahren Sie mit [Ein Kling Omni-Video abrufen](./omni-query) fort, bis der Task abgeschlossen ist.
Verschieben Sie die zurückgegebene MP4-URL in Ihren eigenen Speicher, wenn Sie dauerhaften Zugriff benötigen.
## 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: >-
Optional model ID for this Kling Omni video request. Omit
this field to use the route default.
prompt:
type: string
description: >-
Text prompt describing the desired video. Maximum length is
2,500 characters. When you send `image_list`, reference the
image with `<<>>`.
image_list:
type: array
description: >-
Optional first-frame image reference for image-referenced
Omni generation.
items:
type: object
required:
- image_url
- type
properties:
image_url:
type: string
description: Image URL or Base64 image string.
type:
type: string
description: >-
Reference role for this image. Use `first_frame` for
the first video frame.
enum:
- first_frame
additionalProperties: false
sound:
type: string
description: Whether to generate audio with the video. Use `on` or `off`.
enum:
- 'on'
- 'off'
default: 'off'
mode:
type: string
description: >-
Generation mode. Use `std` for standard generation or `pro`
when the selected model supports the higher-quality mode.
enum:
- std
- 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 for text-to-video and first-frame
image-reference workflows. Use `5` or `10` as a string.
default: '5'
enum:
- '5'
- '10'
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: std
aspect_ratio: '16:9'
duration: '5'
sound: 'off'
examples:
Text to video:
summary: Kling Omni text-to-video request
value:
model_name: kling-v3-omni
prompt: A paper boat drifts across a calm pond at sunrise.
mode: std
aspect_ratio: '16:9'
duration: '5'
sound: 'off'
Image reference:
summary: Kling Omni first-frame request
value:
model_name: kling-video-o1
prompt: Animate <<>> with a slow camera move.
image_list:
- image_url: https://your-image-host/first-frame.png
type: first_frame
mode: std
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: Text to video
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": "std",
"aspect_ratio": "16:9",
"duration": "5",
"sound": "off"
}'
- lang: Python
label: Text to video
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": "std",
"aspect_ratio": "16:9",
"duration": "5",
"sound": "off"
},
)
result = response.json()
print(result.get("code"), result.get("data", {}).get("task_id"))
- lang: JavaScript
label: Text to video
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": "std",
"aspect_ratio": "16:9",
"duration": "5",
"sound": "off"
}),
});
const result = await response.json();
console.log(result.code, result.data?.task_id);
- lang: Shell
label: Image reference
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-video-o1",
"prompt": "Animate <<>> with a slow camera move.",
"image_list": [
{
"image_url": "https://your-image-host/first-frame.png",
"type": "first_frame"
}
],
"mode": "std",
"aspect_ratio": "16:9",
"duration": "5",
"sound": "off"
}'
- lang: Python
label: Image reference
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-video-o1",
"prompt": "Animate <<>> with a slow camera move.",
"image_list": [
{
"image_url": "https://your-image-host/first-frame.png",
"type": "first_frame"
}
],
"mode": "std",
"aspect_ratio": "16:9",
"duration": "5",
"sound": "off"
},
)
result = response.json()
print(result.get("code"), result.get("data", {}).get("task_id"))
- lang: JavaScript
label: Image reference
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-video-o1",
"prompt": "Animate <<>> with a slow camera move.",
"image_list": [
{
"image_url": "https://your-image-host/first-frame.png",
"type": "first_frame"
}
],
"mode": "std",
"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.
````