Video Generation

Generate AI videos from text prompts using Google Veo 3.1 — the latest video generation model from Google DeepMind.

⏱️ Processing Time

Videos take 45 seconds to 5 minutes to generate depending on the model. Use wait: true for sync mode, or poll the job status endpoint.

POST/v1/videos/generations

Request Body

Parameter	Type	Required	Description
`model`	string	No	Model to use (default: veo-3.1-fast-low)
`prompt`	string	Yes	Text description of the video
`orientation`	string	No	Video orientation (landscape, portrait)
`wait`	boolean	No	Wait for completion (true) or return job ID (false)

Available Video Models

Model ID	Provider	Speed	Quality
`veo-3.1`	Google DeepMind	~2-5 min	Highest
`veo-3.1-fast`	Google DeepMind	~1-2 min	High
`veo-3.1-fast-low`	Google DeepMind	~45s ⚡	Good (recommended)
`grok-imagine-1.0-video`	xAI	~1-2 min	Good

Sync Mode (wait for result)

cURL

curl https://api.zora.io.vn/v1/videos/generations \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "veo-3.1-fast-low", "prompt": "Ocean waves crashing on a beach at sunset, cinematic 4K", "orientation": "landscape", "wait": true }'

Response (200)

JSON

{ "id": "vid_lxyz789", "status": "completed", "video_url": "https://storage.googleapis.com/...", "elapsed": 45, "model": "veo-3.1-fast-low" }

Async Mode (poll for result)

cURL — Start

curl https://api.zora.io.vn/v1/videos/generations \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "veo-3.1-fast-low", "prompt": "A golden retriever puppy running through a garden" }'

Response (202)

JSON

{ "id": "vid_lxyz789", "status": "processing", "model": "veo-3.1-fast-low" }

GET/v1/videos/generations/:id

Poll until status is "completed" or "failed"

Poll Response

JSON

// Processing { "id": "vid_lxyz789", "status": "processing", "elapsed": 30 } // Completed { "id": "vid_lxyz789", "status": "completed", "video_url": "https://storage.googleapis.com/...", "elapsed": 45 }

Python Example

Python

import requests, time API = "https://api.zora.io.vn/v1" HEADERS = { "Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json" } # Start video generation resp = requests.post(f"{API}/videos/generations", headers=HEADERS, json={ "model": "veo-3.1-fast-low", "prompt": "A cat sleeping on a cozy blanket, 4K cinematic" }) job = resp.json() job_id = job["id"] print(f"Job started: {job_id}") # Poll for completion while True: status = requests.get(f"{API}/videos/generations/{job_id}", headers=HEADERS).json() if status["status"] == "completed": print(f"Video URL: {status['video_url']}") break elif status["status"] == "failed": print(f"Failed: {status.get('error')}") break time.sleep(10) print(f" Waiting... {status.get('elapsed', '?')}s")