Skip to main content
POST
  • Use gemini-omni-flash-preview-official in the model field
  • Supports text-to-video, image/reference-to-video, and video editing
  • Supports up to 10 reference images or up to 3 input videos; images and videos cannot be mixed
  • Video duration is limited to 10 seconds; the Playground offers 4 / 6 / 8 / 10 second presets
  • Only 720p resolution is supported; both 16:9 and 9:16 aspect ratios are available
  • Async task API: submit a task, then query by task ID
This page documents gemini-omni-flash-preview-official. The platform routes it through the Vertex AI Interactions API with Service Account OAuth, not the Vertex AI Publisher Model predictLongRunning endpoint. It is separate from the legacy gemini-omni-flash / gemini_omni_flash model.
Upload local images with the Upload 画像API and local videos with the Upload Video API first, then pass the returned URLs. Do not pass base64 media data directly.

Authorizations

string
必須
Use Bearer Token authentication:

Body

string
デフォルト:"gemini-omni-flash-preview-official"
必須
モデル name. Use gemini-omni-flash-preview-official.
string
必須
Text prompt for video generation.
integer
デフォルト:"6"
Video duration in seconds. The maximum is 10; the Playground offers 4, 6, 8, and 10 second presets.
string
デフォルト:"16:9"
Video aspect ratio:
  • 16:9 landscape
  • 9:16 portrait
string
デフォルト:"720p"
Video resolution:
  • 720p default resolution
  • Only 720p is supported; Veo-specific parameters are not accepted
string[]
Optional reference image URL array with up to 10 items. Omit it for text-to-video. This field cannot be combined with video_list.
object[]
Optional input videos for video editing, with up to 3 items. Each object must contain video_url. This field cannot be combined with image_urls.
object
Optional generation controls: temperature, topP / top_p, candidateCount / candidate_count, previous_interaction_id, and task (text_to_video, image_to_video, reference_to_video, or edit).

レスポンス

string
Task ID for status polling.
string
Object type, usually generation.task.
string
モデル name used for the request.
string
Task status: queued, in_progress, completed, or failed.
integer
Task creation timestamp.
string
Generated video URL when the task completes.

Examples

Query Task

The generation endpoint returns a task ID. Use the common video task status endpoint to fetch status and results: