Skip to main content
POST
/
v3
/
async
/
veo-3.1-generate-reference
Veo 3.1 Reference Image Video Generation
curl --request POST \
  --url https://api.highwayapi.ai/v3/async/veo-3.1-generate-reference \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "seed": 123,
  "prompt": "<string>",
  "resolution": "<string>",
  "aspect_ratio": "<string>",
  "sample_count": 123,
  "enhance_prompt": true,
  "generate_audio": true,
  "negative_prompt": "<string>",
  "reference_images": [
    {}
  ],
  "person_generation": "<string>"
}
'
{
  "task_id": "<string>"
}
Use the Google Veo 3.1 model to generate videos guided by 1–3 reference images. Supports 720p and 1080p resolutions, as well as 16:9 and 9:16 aspect ratios. The duration is fixed at 8 seconds. The reference type only supports asset.
This is an asynchronous API and only returns the task_id of the asynchronous task. You should use this task_id to request the Get Task Result API to retrieve the generated result.

​
Request Headers

​
Content-Type
string
required
Enum value: application/json
​
Authorization
string
required
Bearer authentication format: Bearer {{API Key}}.

​
Request Body

​
seed
integer
Random seed used to reproduce generation results.Value range: [0, 4294967295]
​
prompt
string
required
Text prompt describing the desired video content.
​
resolution
string
default:"720p"
Output video resolution.Available values: 720p, 1080p
​
aspect_ratio
string
default:"16:9"
Output video aspect ratio.Available values: 16:9, 9:16
​
sample_count
integer
default:1
Number of video samples to generate (1–4).Value range: [1, 4]
​
enhance_prompt
boolean
default:true
Whether to use AI to rewrite the prompt for better generation results.
​
generate_audio
boolean
default:false
Whether to generate audio at the same time.
​
negative_prompt
string
Describes content to avoid in the generated video.
​
reference_images
array
required
1–3 reference images used to guide video generation. Each element contains an image URL or Base64-encoded data and the reference type.Array length: 1 - 3
​
person_generation
string
default:"allow_adult"
Whether to allow generating adult people. allow_adult: allow generating adults; dont_allow: do not allow generating people.Available values: allow_adult, dont_allow

​
Response Information

​
task_id
string
Use task_id to request the Get Task Result API to retrieve the generated output.