Create video using Veo2 and Veo3 models

June 18, 2025 (August 25, 2025)

Table of contents

  1. Request Headers
  2. Request Body
  3. Responses
  4. Model
  5. Examples
  6. Try It

This endpoint creates a video using Google’s Veo models.

Parameter Veo2 (image+text to video) Veo3 (image+text to video) Veo3-Fast (text to video)
prompt Optional Optional Optional
startAssetId Required Optional Optional
duration, sec 5 (default), 6, 7, 8 8 (default) 8 (default)
aspectRatio 16:9 (default), 9:16 16:9 (default) 16:9 (default)
audioSFX Optional Optional Optional
resolution not supported (720p) 720p/1080p (default) 720p/1080p (default)

https://api.useapi.net/v1/ltxstudio/videos/veo-create

Request Headers 
Authorization: Bearer {API token}
Content-Type: application/json
# Alternatively you can use multipart/form-data
# Content-Type: multipart/form-data
Request Body 
{
  "prompt": "A serene landscape with flowing water",
  "startAssetId": "asset:3b18…-type:image/png",
  "model": "veo2",
  "duration": "5",
  "aspectRatio": "16:9",
  "audioSFX": true,
  "seed": 123456
}
  • email is optional when only one account configured.
    However, if you have multiple accounts configured, this parameter becomes required.
  • model is optional, Veo model to use.
    Supported values: veo2, veo3, veo3-fast.
    Default is veo2.
  • prompt is optional, text description for video generation (max 2000 characters)
  • startAssetId is optional, asset ID for the starting frame. Use field fileId from POST assets/?type=reference-image or GET assets/?filter=images.
  • duration is optional, video duration in seconds.
  • aspectRatio is optional, video aspect ratio.
  • audioSFX is optional, enable automatic sound effects generation.
    Available for all models. For veo2, generates separate audio track.
    For veo3 and veo3-fast, controls whether to include audio in video generation.
    Default is false.
  • resolution is optional, available for veo3 and veo3-fast.
    Supported values: 720p, 1080p (default).
  • seed is optional, random seed for reproducible results.
    Default is random.
  • pollForResult is optional, number of polling attempts to wait for completion (each attempt waits 3 seconds, up to 60 seconds total max) before sending job to the scheduler.
    For example, pollForResult: 5 will poll every 3 seconds for up to 15 seconds total.
    Supported values: 1-20.
    Default is immediate return with jobId.
  • maxJobs is optional, override the default maximum number of concurrent jobs.
  • replyUrl is optional, webhook URL for job completion notifications.
    See GET assets/jobId for response model.
  • replyRef is optional, custom reference for webhook identification.
Responses

  • 200 OK (Job Created)

    {
    "jobId": "email:[email protected]:7a34b821-9fd0-205e-d21b-4abc6f7839e7-type:video",
    "generationId": "gen_abc123def456"
}

  • 200 OK (pollForResult completed)

    {
    "status": {
        "type": "completed",
        "progress": 100,
        "artifact": {
            "assetUrl": "https://storage.googleapis.com/lt-infinity-prd/artifacts/vertex-ai/…",
            "expirationDateString": "1748919477350",
            "asset": {
                "type": "artifact",
                "fileId": "asset:3b18…-type:video/mp4",
                "mimeType": "video/mp4",
                "artifactSubtype": "vertex-ai"
            }
        }
    },
    "jobId": "email:[email protected]:7a34b821-9fd0-205e-d21b-4abc6f7839e7-type:video",
    "replyRef": "custom-reference-123",
    "replyUrl": "https://webhook.example.com/ltx-callback",
    "code": 200
}

  • 400 Bad Request

    {
  "error": "Error message",
  "code": 400
}

  • 401 Unauthorized

    {
  "error": "Unauthorized",
  "code": 401
}

  • 402 Payment Required

    {
  "error": "Insufficient credits",
  "code": 402
}
Model

Use GET assets/jobId to retrieve job status and results if they were not provided with the response.

{ // TypeScript, all fields are optional
    status: {
        type: 'active' | 'completed' | 'failed'
        progress?: number
        message?: string
        artifact?: {
            assetUrl: string
            expirationDateString: string
            asset: {
                type: string
                fileId: string
                mimeType: string
                artifactSubtype: string
            }
        }
    }
    jobId?: string
    generationId?: string
    replyRef?: string
    replyUrl?: string
    code?: number
}
Examples 
  • curl "https://api.useapi.net/v1/ltxstudio/videos/veo-create" \
   -H "Authorization: Bearer …" \
   -H "Content-Type: application/json" \
   -d '{
     "prompt": "A serene landscape with flowing water",
     "startAssetId": "asset:3b18…-type:image/png",
     "model": "veo3-fast",
     "audioSFX": true,
     "pollForResult": 10
   }'

  • const token = "API token";
const apiUrl = "https://api.useapi.net/v1/ltxstudio/videos/veo-create";

const response = await fetch(apiUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${token}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "prompt": "A serene landscape with flowing water",
    "startAssetId": "asset:3b18…-type:image/png",
    "model": "veo3-fast",
    "audioSFX": true,
    "pollForResult": 10
  })
});
const result = await response.json();
console.log("response", {response, result});

  • import requests
token = "API token"
apiUrl = "https://api.useapi.net/v1/ltxstudio/videos/veo-create"
headers = {
    "Authorization" : f"Bearer {token}",
    "Content-Type": "application/json"
}
data = {
    "prompt": "A serene landscape with flowing water",
    "startAssetId": "asset:3b18…-type:image/png",
    "model": "veo3-fast",
    "audioSFX": True,
    "pollForResult": 10
}
response = requests.post(apiUrl, headers=headers, json=data)
print(response, response.json())
Try It