Skip to main content
Available now on ModelsLab · Video Generation

Veo 3.1Cinematic Videos Instant

Try Veo 3.1API Documentation

Master Veo 3.1 API

Native Audio

Synchronized Sound Effects

Veo 3.1 generates richer audio matching video actions and dialogue.

Image to Video

Consistent Character Scenes

Upload images for Veo 3.1 to maintain subjects across multi-shot videos.

Frame Control

First Last Transitions

Bridge start and end frames with smooth motion in Veo 3.1 API.

Endpoints

Multiple endpoints, one model

Veo 3.1 is available through 2 specialized endpoints. Choose the one that fits your workflow.

Veo 3.1Veo-3.1Veo 3.1 Image to Videoveo3.1-image2video

Examples

See what Veo 3.1 can create

Copy any prompt below and try it yourself in the playground.

Urban Timelapse

“Cinematic time-lapse of a bustling city skyline at dusk, cars streaming lights, smooth dolly zoom out, synchronized ambient traffic sounds and distant horns, 1080p, 16:9 aspect ratio.”

Ocean Waves

“Serene ocean waves crashing on rocky shore during golden hour, slow motion foam details, natural wave sounds and seagull calls, high fidelity 1080p, portrait 9:16.”

Mountain Drone

“Aerial drone shot soaring over snow-capped mountains at sunrise, mist rolling through valleys, wind and echo effects, sharp 1080p landscape 16:9.”

City Lights

“Neon-lit street at night with rain reflections, over-the-shoulder walk through crowd, synced footsteps and city hum, 1080p vertical 9:16.”

For Developers

A few lines of code.
Videos from text. One call.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per second, no minimums
  • Python and JavaScript SDKs, plus REST API
API Documentation 
import requests


response = requests.post(
    "https://modelslab.com/api/v7/video-fusion/text-to-video",
    json={
  "key": "YOUR_API_KEY",
  "prompt": "A wide, eye-level cinematic shot captures a man walking slowly across a frost-covered bridge at dawn, his hands tucked into the pockets of a heavy coat. Pale morning light glows faintly through soft, curling fog that clings to the bridge railings. In the distance, bare trees fade into the mist, their skeletal branches barely visible. The pace is unhurried and reflective, evoking a naturalistic and quiet mood. The scene is filled with subtle, atmospheric sounds—faint footsteps crunching on frost, steady breaths in the cold air, and the distant caw of a crow echoing across the stillness.",
  "duration": "8",
  "aspect_ratio": "16:9",
  "generate_audio": ""
}
)
print(response.json())

FAQ

Common questions about Veo 3.1

Read the docs

Veo 3.1 creates 1080p videos from text or images with native audio. Supports 4-8 second clips in 16:9 or 9:16 ratios. Includes character consistency and cinematic controls.

Call veo-3.1-generate-001 endpoint with text or image inputs. Outputs MP4 videos with C2PA metadata. Fast variant optimizes speed.

Upload reference images to guide scenes and maintain consistency. Generates transitions or extensions with audio. Ideal for multi-shot narratives.

Veo 3.1 API provides direct access without Google's ecosystem limits. Matches capabilities like 1080p upscaling and frame interpolation.

Native 720p/1080p at 24 FPS, with upscaling to 4K. Portrait and landscape aspect ratios available.

Yes, preview feature extends existing clips. Use first-last frame for smooth transitions between images.

Ready to create?

Start generating with Veo 3.1 on ModelsLab.

Try Veo 3.1API Documentation