DEV Community

q2408808
q2408808

Posted on

Veo 3.1 API Tutorial: Complete Python & JavaScript Guide (2026)

#javascript #tutorial #python #ai

Veo 3.1 API Tutorial: Complete Python & JavaScript Guide (2026)

TL;DR: Google's Veo 3.1 is the most advanced AI video generation model available. This guide covers every feature — text-to-video, image-to-video, aspect ratio control, resolution control, scene extension, and reference images — using NexaAPI for instant access at 67% lower cost than direct Google API pricing.

What is Veo 3.1?

Veo 3.1 is Google's state-of-the-art AI video generation model (updated January 2026). It generates high-fidelity 8-second videos at up to 4K resolution with native audio — the first video generation model to natively synchronize sound effects, music, and dialogue with video content.

Key Features:

  • Native Audio Generation: Natural conversations, synchronized sound effects
  • Text-to-Video & Image-to-Video
  • Reference Images: Guide generation with up to 3 reference images
  • Scene Extension: Extend videos up to 1 minute+
  • Resolution: 720p, 1080p, or 4K
  • Aspect Ratios: 16:9, 9:16, 1:1

The Problem with Direct Google API

Google's Veo 3.1 API costs $0.40/second ($3.20 per 8-second 1080p video), requires GCP setup, and has no free tier.

NexaAPI solves this: same Veo 3.1 model, instant access, $0.1333/second (67% cheaper), with a free tier.

Installation 

# Python
pip install nexaapi

# JavaScript
npm install nexaapi
Enter fullscreen mode Exit fullscreen mode

Get your API key at nexa-api.com — no credit card required for free tier.

Feature 1: Text-to-Video

Python 

from nexaapi import NexaAPI

client = NexaAPI(api_key='YOUR_API_KEY')

response = client.video.generate(
    model='veo-3.1',
    prompt='A timelapse of a flower blooming in a garden, macro photography, golden hour lighting'
)

print('Video URL:', response.video_url)
Enter fullscreen mode Exit fullscreen mode

JavaScript 

import NexaAPI from 'nexaapi';

const client = new NexaAPI({ apiKey: 'YOUR_API_KEY' });

const response = await client.video.generate({
  model: 'veo-3.1',
  prompt: 'A timelapse of a flower blooming in a garden, macro photography'
});

console.log('Video URL:', response.videoUrl);
Enter fullscreen mode Exit fullscreen mode

Feature 2: Aspect Ratio Control 

# Portrait for TikTok/Reels
portrait = client.video.generate(
    model='veo-3.1',
    prompt='A person walking through neon-lit Tokyo at night',
    aspect_ratio='9:16'
)

# Landscape for YouTube
landscape = client.video.generate(
    model='veo-3.1',
    prompt='Epic mountain landscape with storm clouds',
    aspect_ratio='16:9'
)

# Square for Instagram
square = client.video.generate(
    model='veo-3.1',
    prompt='Coffee being poured in slow motion',
    aspect_ratio='1:1'
)
Enter fullscreen mode Exit fullscreen mode

Feature 3: Resolution Control (720p, 1080p, 4K) 

# 4K cinematic quality
uhd_video = client.video.generate(
    model='veo-3.1',
    prompt='A majestic eagle soaring over snow-capped mountains, golden hour',
    resolution='4k',
    aspect_ratio='16:9'
)

print('4K video:', uhd_video.video_url)
Enter fullscreen mode Exit fullscreen mode

Feature 4: Image-to-Video 

# Animate a still image
product_video = client.video.generate(
    model='veo-3.1',
    prompt='The product rotates slowly on a white background, studio lighting',
    image_url='https://example.com/product.jpg',
    aspect_ratio='1:1'
)

print('Animated video:', product_video.video_url)
Enter fullscreen mode Exit fullscreen mode 
// JavaScript image-to-video
const i2v = await client.video.generate({
  model: 'veo-3.1',
  prompt: 'The landscape comes alive with gentle wind and moving clouds',
  imageUrl: 'https://example.com/landscape.jpg',
  aspectRatio: '16:9'
});

console.log('Image-to-Video:', i2v.videoUrl);
Enter fullscreen mode Exit fullscreen mode

Feature 5: Reference Images 

# Use up to 3 reference images for consistency
character_video = client.video.generate(
    model='veo-3.1',
    prompt='The character walks through a futuristic city, confident stride',
    reference_images=[
        'https://example.com/character-front.jpg',
        'https://example.com/character-side.jpg'
    ],
    aspect_ratio='9:16'
)
Enter fullscreen mode Exit fullscreen mode

Feature 6: Batch Generation 

import asyncio
from nexaapi import AsyncNexaAPI

async def generate_batch():
    client = AsyncNexaAPI(api_key='YOUR_API_KEY')

    prompts = [
        'A rocket launching into space, cinematic',
        'A chef preparing sushi in a professional kitchen',
        'A sports car drifting on a mountain road at sunset'
    ]

    tasks = [
        client.video.generate(model='veo-3.1', prompt=p, aspect_ratio='16:9')
        for p in prompts
    ]

    results = await asyncio.gather(*tasks)

    for i, result in enumerate(results):
        print(f'Video {i+1}: {result.video_url}')

asyncio.run(generate_batch())
Enter fullscreen mode Exit fullscreen mode 
// JavaScript batch with Promise.all
const prompts = [
  'A rocket launching into space',
  'A chef preparing sushi',
  'Sports car drifting at sunset'
];

const results = await Promise.all(
  prompts.map(prompt => client.video.generate({ model: 'veo-3.1', prompt, aspectRatio: '16:9' }))
);

results.forEach((r, i) => console.log(`Video ${i+1}:`, r.videoUrl));
Enter fullscreen mode Exit fullscreen mode

Pricing Comparison

Provider Price/Second 8s Video (1080p) Free Tier
NexaAPI ⭐ $0.1333 $1.07 ✅ Yes
Google Gemini API $0.40 $3.20 ❌ No
Google Vertex AI $0.40 $3.20 ❌ No

NexaAPI saves you 67% vs direct Google API pricing.

Get Started

  1. Sign up free at nexa-api.com — no credit card required
  2. Install: pip install nexaapi (PyPI) or npm install nexaapi (npm)
  3. Also available on RapidAPI

Happy building! 🎬

Official Veo 3.1 docs: ai.google.dev/gemini-api/docs/video

Top comments (0)