> ## Documentation Index
> Fetch the complete documentation index at: https://docs.omniall.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Create video

> Create a Google Omni video task.

**Path:** `POST https://api.omniall.ai/v1/videos`

**Same endpoint, different use cases:** text-to-video · reference images · first/last frame · video reference (`omni-fast-v2v`).

Auth: `Authorization: Bearer sk-...`



## OpenAPI

````yaml openapi/google-omni-video.yaml POST /v1/videos
openapi: 3.1.0
info:
  title: Omniall AI — Google Omni video
  version: 1.0.0
  description: >-
    Google Omni async video via OpenAI-style Video API.


    **Create:** `POST https://api.omniall.ai/v1/videos`


    **Poll:** `GET /v1/videos/{task_id}`


    Models: `omni-fast` (text / image / first-last frame), `omni-fast-v2v`
    (video reference).


    Auth: `Authorization: Bearer sk-...`
servers:
  - url: https://api.omniall.ai
security: []
paths:
  /v1/videos:
    post:
      tags:
        - Google Omni
      summary: Create video
      description: >-
        Create a Google Omni video task.


        **Path:** `POST https://api.omniall.ai/v1/videos`


        **Same endpoint, different use cases:** text-to-video · reference images
        · first/last frame · video reference (`omni-fast-v2v`).


        Auth: `Authorization: Bearer sk-...`
      operationId: googleOmniCreateVideo
      parameters:
        - name: Authorization
          in: header
          required: true
          schema:
            type: string
            example: Bearer sk-...
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - model
                - prompt
              properties:
                model:
                  type: string
                  description: '`omni-fast` or `omni-fast-v2v` (video reference).'
                  example: omni-fast
                prompt:
                  type: string
                  description: Text prompt (motion / camera / subject).
                first_image_url:
                  type: string
                  description: >-
                    First-frame image URL or base64. Required with
                    last_image_url.
                last_image_url:
                  type: string
                  description: >-
                    Last-frame image URL or base64. Must use with
                    first_image_url.
                video:
                  type: string
                  description: >-
                    Reference video (MP4 URL or data URI). Aliases: `video_url`,
                    `input_video`.
                video_url:
                  type: string
                input_video:
                  type: string
                seconds:
                  type: string
                  description: Duration seconds, suggested 4–30. Example `"8"`.
                aspect_ratio:
                  type: string
                  description: e.g. `16:9`, `9:16`.
                resolution:
                  type: string
                  description: e.g. `720p`, `1080p`, `2k`, `4k`.
                images:
                  type: array
                  maxItems: 5
                  items:
                    type: string
                  description: Up to 5 reference images (URL or base64).
            examples:
              text_to_video:
                summary: Text-to-video
                value:
                  model: omni-fast
                  prompt: >-
                    Ocean waves gently rolling onto a beach at golden hour,
                    cinematic, warm sunlight
                  seconds: '8'
                  aspect_ratio: '16:9'
                  resolution: 720p
              reference_images:
                summary: Reference images
                value:
                  model: omni-fast
                  prompt: Keep the character look; walk through a neon alley
                  images:
                    - https://example.com/character.jpg
                  seconds: '8'
                  aspect_ratio: '9:16'
                  resolution: 720p
              first_last_frame:
                summary: First / last frame
                value:
                  model: omni-fast
                  prompt: Smooth transition from dawn to dusk over the same landscape
                  first_image_url: https://example.com/first-frame.jpg
                  last_image_url: https://example.com/last-frame.jpg
                  seconds: '8'
                  aspect_ratio: '16:9'
                  resolution: 1080p
              video_reference:
                summary: Video reference (v2v)
                value:
                  model: omni-fast-v2v
                  prompt: >-
                    Edit the attached video into a visibly new version; keep
                    subject, change lighting
                  video: https://example.com/source.mp4
                  seconds: '8'
                  aspect_ratio: '16:9'
                  resolution: 720p
      responses:
        '200':
          description: Task accepted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VideoTask'
              example:
                id: task_xxxxxxxx
                task_id: task_xxxxxxxx
                object: video
                model: omni-fast
                status: queued
                progress: 0
                created_at: 1775025000
components:
  schemas:
    VideoTask:
      type: object
      properties:
        id:
          type: string
        task_id:
          type: string
        object:
          type: string
        model:
          type: string
        status:
          type: string
        progress:
          type: integer
        created_at:
          type: integer
        completed_at:
          type: integer
        video_url:
          type: string
        error:
          type: object

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.