Skip to main content
POST
Veo 3.1 Fast Image-to-Video
The Veo 3.1 Preview API is automatically compatible with this endpoint
Use the Veo 3.1 Fast video generation model to generate high-quality video content from an input image and text description. This endpoint uses asynchronous processing, and you need to query the final generated result using the task_id.

Request Headers

string
required
Enum value: application/json
string
required
Bearer authentication format: Bearer {{API Key}}.

Request Body

string
required
A text string describing the video you want to generate.
string
The input image, supporting either a URL or base64 encoding.
string
The ending image, used to fill the last frame of the video. Supports either a URL or base64 encoding.
string
Specifies the aspect ratio of the generated video.Enum values: 16:9, 9:16. The default value is 16:9.
integer
The length, in seconds, of the video file you want to generate.Enum values: 4, 6, 8. The default value is 8.
boolean
Specifies whether to use Gemini to enhance your prompt. Only true is supported.Default value: true
boolean
required
Specifies whether to generate audio for the video.
string
A text string describing the content you want to prevent the model from generating.
string
Safety setting that controls whether person or face generation is allowed.Enum values:
  • allow_adult (default): Only allows generation of adults
  • dont_allow: Does not allow people or faces to be included in the image
  • allow_all: Allows generation of people of all ages (requires the project to be in the allowlist)
string
The resolution of the generated video.Enum values: 720p (default) or 1080p
integer
The number of video samples to generate.Value range: 1-4
uint32
A number used to initialize the random generation process. Using the same seed, prompt, and other parameters will produce the same output video, making the generation process deterministic.Value range: 0-4,294,967,295

Response Parameters

string
required
The task_id of the asynchronous task. You should use this task_id to request the Get Task Result API to obtain the generated result