> ## 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 > Create a Kling Omni video task with the model ID in the URL, then retrieve the result by task ID. Use `POST /omni-video/{model}` to create an asynchronous Kling Omni video task. Place the model ID in the URL and provide the input in `contents`. ## Choose a model * `kling-3.0-omni`: `720p`, `1080p`, or `4k`; 3-15 seconds; `native`, `original`, or `off` audio. * `kling-o1`: `720p` or `1080p`; 3-10 seconds; `original` or `off` audio. The text-only example uses `kling-3.0-omni`. To create a silent video, set `settings.audio` to `off`. ## Request parameters | Field | Required | Description | | -------------------------------- | ------------------------ | ----------------------------------------------------------------------------------------------------------------------------- | | `model` | Yes | Model ID in the URL. Choose an ID from the list above. | | `contents` | Yes | Nonempty array of video inputs. For a text-only request, include a `prompt` item. | | `contents[].type` | Yes | `prompt`, `first_frame`, `last_frame`, `refer_image`, `feature_video`, or `base_video`. A `last_frame` needs a `first_frame`. | | `contents[].text` | For a `prompt` item | Text that describes the video. | | `contents[].url` | For image or video items | Image URL or Base64 image data; video items use a public video URL. | | `settings.resolution` | No | Output resolution. If omitted, the request uses `720p`. Available values depend on `model`. | | `settings.aspect_ratio` | No | Frame shape: `16:9`, `9:16`, or `1:1`. If omitted, the request uses `16:9`. | | `settings.duration` | No | Video length in whole seconds. If omitted, the request uses 5 seconds. Use a duration within the selected model's range. | | `settings.multi_shot` | No | Boolean multi-shot setting. Set explicitly; the example uses `false` for a single continuous shot. | | `settings.audio` | No | Audio choice for the selected model. If omitted, the request uses `off`. | | `options.callback_url` | No | HTTPS URL that receives task status callbacks. | | `options.external_task_id` | No | Your own task identifier for correlation; retain the returned `data.id` for queries. | | `options.watermark_info.enabled` | No | Set to `true` to request a watermark. | For `kling-3.0-omni`, a `feature_video` input requires `settings.multi_shot: true` and `settings.audio: off`. A `base_video` input requires `settings.multi_shot: false` and cannot use `settings.audio: native`. Do not combine `base_video` with a first or last frame. To create a five-second text-only video, send this request body to `POST /omni-video/kling-3.0-omni`: ```json theme={null} { "contents": [ { "type": "prompt", "text": "A paper boat drifts on a pond." } ], "settings": { "resolution": "720p", "aspect_ratio": "16:9", "duration": 5, "multi_shot": false, "audio": "off" } } ``` The response returns an `id` for the asynchronous task: ```json theme={null} { "code": 0, "message": "SUCCEED", "data": { "id": "example-task-id", "status": "submitted" } } ``` Use the `data.id` value with [Get a Kling task](./tasks) until the task completes. Read the finished video URL from the task's `outputs` array. Store the video in your own storage if you need durable access. The OpenAPI panel contains matching Shell, Python, and JavaScript requests. For more input combinations, see the [Kling 3.0 Omni video API reference](https://kling.ai/document-api/api/video/3-0-omni/video-omni) or [Kling O1 Omni video API reference](https://kling.ai/document-api/api/video/o1/video-omni). ## OpenAPI ````yaml api/openapi/video/kling/model-routes/post-omni-video.openapi.json POST /omni-video/{model} openapi: 3.1.0 info: title: Kling Omni video model routes version: 1.0.0 description: Create a Kling Omni video task with a model ID in the URL. servers: - url: https://api.cometapi.com security: - bearerAuth: [] paths: /omni-video/{model}: post: summary: Create a Kling Omni video task description: Submit video inputs and save the returned task ID for status queries. operationId: createKlingModelRouteOmniVideo parameters: - name: model in: path required: true description: >- Kling Omni model ID. The selected model controls resolution, duration, and audio choices. schema: type: string enum: - kling-3.0-omni - kling-o1 example: kling-3.0-omni requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/OmniVideoRequest' example: contents: - type: prompt text: A paper boat drifts on a pond. settings: resolution: 720p aspect_ratio: '16:9' duration: 5 multi_shot: false audio: 'off' responses: '200': description: Task created. Store `data.id` for a `GET /tasks` query. content: application/json: schema: $ref: '#/components/schemas/SubmitResponse' example: code: 0 message: SUCCEED data: id: example-task-id status: submitted x-codeSamples: - lang: Shell label: Create task source: | curl https://api.cometapi.com/omni-video/kling-3.0-omni \ -H "Authorization: Bearer $COMETAPI_KEY" \ -H "Content-Type: application/json" \ --data-binary @- <<'JSON' { "contents": [ { "type": "prompt", "text": "A paper boat drifts on a pond." } ], "settings": { "resolution": "720p", "aspect_ratio": "16:9", "duration": 5, "multi_shot": false, "audio": "off" } } JSON - lang: Python label: Create task source: | import os import requests response = requests.post( "https://api.cometapi.com/omni-video/kling-3.0-omni", headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]}, json={ "contents": [ { "type": "prompt", "text": "A paper boat drifts on a pond.", } ], "settings": { "resolution": "720p", "aspect_ratio": "16:9", "duration": 5, "multi_shot": False, "audio": "off", }, }, ) response.raise_for_status() result = response.json() print(result["data"]["id"]) - lang: JavaScript label: Create task source: | const response = await fetch( "https://api.cometapi.com/omni-video/kling-3.0-omni", { method: "POST", headers: { Authorization: `Bearer ${process.env.COMETAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "contents": [ { "type": "prompt", "text": "A paper boat drifts on a pond." } ], "settings": { "resolution": "720p", "aspect_ratio": "16:9", "duration": 5, "multi_shot": false, "audio": "off" } }), }, ); if (!response.ok) throw new Error(`HTTP ${response.status}`); const result = await response.json(); console.log(result.data.id); components: schemas: OmniVideoRequest: type: object required: - contents properties: contents: type: array minItems: 1 description: Video input items. Send a prompt item for text-only generation. items: $ref: '#/components/schemas/ContentItem' settings: $ref: '#/components/schemas/OmniSettings' options: $ref: '#/components/schemas/TaskOptions' additionalProperties: false SubmitResponse: type: object required: - code - message - data properties: code: type: - integer - string description: Result code. `0` indicates task creation. message: type: string description: Result message. msg: type: string description: Additional result message, when included. data: type: object description: Task identification and submission status. required: - id - status properties: id: type: string description: System task ID for a `GET /tasks` query. status: type: string enum: - submitted - processing - succeeded - failed description: Task status. ContentItem: type: object required: - type properties: type: type: string enum: - prompt - first_frame - last_frame - refer_image - feature_video - base_video description: >- Input role. Use `prompt` for text, an image role for a frame or image reference, or a video role for a video reference. A last frame requires a first frame. text: type: string maxLength: 3072 description: Text prompt, required when `type` is `prompt`. url: type: string description: >- Required for non-prompt items. Image items accept a public URL or Base64 JPG/PNG; video items accept a public MP4/MOV URL. allOf: - if: properties: type: const: prompt description: Text-prompt input role. then: required: - text else: required: - url additionalProperties: false OmniSettings: type: object description: >- Output settings. Set multi_shot and audio explicitly for the intended result. properties: resolution: type: string enum: - 720p - 1080p - 4k default: 720p description: Output resolution. `4k` applies only to `kling-3.0-omni`. aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' default: '16:9' description: Output frame shape. duration: type: integer minimum: 3 maximum: 15 default: 5 description: >- Requested duration in whole seconds. `kling-o1` accepts 3 to 10 seconds; `kling-3.0-omni` accepts 3 to 15 seconds. multi_shot: type: boolean default: false description: >- Set `false` for one continuous shot or `true` for a multi-shot request. audio: type: string enum: - native - original - 'off' default: 'off' description: >- `native` creates audio with `kling-3.0-omni`; `original` retains sound from an input video; `off` makes silent output. `kling-o1` accepts only `original` and `off`. additionalProperties: false TaskOptions: type: object description: Optional task notification and identification settings. properties: callback_url: type: string format: uri description: HTTPS URL that receives task status callbacks. external_task_id: type: string description: >- Your own task identifier, unique within your account. The response still returns the system task ID. watermark_info: type: object description: Watermark setting for the generated output. required: - enabled properties: enabled: type: boolean description: Set to `true` to request a watermarked result. additionalProperties: false additionalProperties: false securitySchemes: bearerAuth: type: http scheme: bearer description: Authenticate with your CometAPI API key. ````