Gemini Native (Video)
Video Series
Gemini Native (Video)
Google Veo video generation models
POST
Gemini Native (Video)
Introduction
Veo is Google Vertex AI’s multimodal video generation model. It supports text-to-video (T2V), first-frame constraint, and first-and-last-frame constraint (3.1 series only) for coherent video generation. Use LeapX’s unified video API: submit a task to get atask_id, then query the task to poll status and get the result.
Authentication
string
required
Bearer Token, e.g.
Bearer sk-xxxxxxxxxxSupported models
Call flow
- Submit task:
POST /v1/video/generationswithmodel,prompt, and Veo-specific parameters. - Poll status:
GET /v1/video/generations/{task_id}untilstatusissucceededorfailed. - Get result: On success,
urlin the response contains the video (Veo may returndata:video/mp4;base64,...or an OSS link).
Veo-specific parameters
string
required
Video generation prompt describing the scene and motion.
integer
default:"4"
Video duration in seconds; supported:
4, 6, 8.string
default:"16:9"
Aspect ratio; only
16:9 and 9:16 supported.string
default:"1080p"
Resolution:
720p, 1080p.string
First-frame reference image (URL or Base64) for image-to-video / first-frame constraint.
string
Last-frame reference image (veo-3.1 series only); use with first frame for start-and-end constraint.
boolean
default:"false"
Whether to generate synchronized audio. Fast models ignore this and always include audio.
integer
default:"1"
Number of videos to generate per request, range
1-4.personGeneration, addWatermark, seed), see Submit Video Task.
