Create Videos with Veo 3.1
Veo 3.1 is Google DeepMind's latest video model. Turn text, images or reference shots into cinematic 4, 6 or 8-second clips at up to 4K, complete with native audio — synchronized dialogue, ambience, music and sound effects.
What is Veo 3.1?
Veo 3.1 is Google DeepMind's flagship video generation model and the successor to Veo 3. It supports text-to-video, image-to-video with a start frame and optional end frame, and reference-to-video that keeps characters and products consistent. Choose the Lite, Fast or Quality tier, render at 720p, 1080p or 4K in 16:9 or 9:16, and get MP4 files with native audio that matches the scene.
Why Choose Veo 3.1?
Up to 4K Resolution
Render at 720p for quick drafts, 1080p for full HD, or 4K for crisp, highly detailed footage ready for large screens and professional edits.
Native Audio & Dialogue
Veo 3.1 generates synchronized audio with every clip: spoken dialogue (put the lines in quotes in your prompt), ambience, music and sound effects that match the action.
Start & End Frame Control
Animate an image as the start frame and optionally add an end frame. Veo 3.1 creates the motion in between for precise, directed transitions.
Reference-to-Video Consistency
Upload 1–3 reference images to keep characters and products consistent from shot to shot. Reference mode produces 8-second clips on the Lite and Fast tiers.
Lite, Fast & Quality Tiers
Pick Lite for budget-friendly iteration, Fast for a balance of speed and detail, or Quality for the highest-fidelity results.
Flexible Length & Format
Generate 4, 6 or 8-second clips in 16:9 landscape or 9:16 portrait, ready for YouTube, TikTok, Reels and ads.
Technical Specifications
Pricing Tiers
Create with Veo 3.1 in 3 Steps
Choose a Mode & Write Your Prompt
Pick text-to-video, image-to-video or reference-to-video. Describe the scene, action, camera and mood, and put any spoken lines in quotes.
Set Tier & Output
Select Lite, Fast or Quality, then choose the duration (4, 6 or 8s), resolution (720p, 1080p or 4K) and aspect ratio (16:9 or 9:16).
Generate & Download
Most videos are ready in about 2 minutes. Download your MP4 with synchronized audio, ready to publish or edit.
What Can You Create with Veo 3.1?
Cinematic Short Films & Trailers
Social Media Ads with Dialogue
Consistent Product & Character Shots
Music Videos & Visual Stories
Veo 3.1 Pricing
Veo 3.1 is charged in credits based on tier, resolution and duration. Lite keeps costs low for drafts, while Quality and 4K deliver maximum fidelity — the exact cost is shown before you generate.
Explore More AI Models
Ready to Create with Veo 3.1?
Generate cinematic AI videos with Google DeepMind's latest model. Up to 4K, native audio and dialogue, and consistent characters from reference images.
Start Creating with Veo 3.1Veo 3.1 FAQ
Common questions about Veo 3.1 video generation
Veo 3.1 is Google DeepMind's latest AI video generation model. It creates 4, 6 or 8-second clips at 720p, 1080p or 4K from text, images or reference images, with native synchronized audio including dialogue, ambience, music and sound effects.
Veo 3.1 is charged in credits based on the tier (Lite, Fast or Quality), resolution and duration you choose. The exact credit cost is shown before you generate, so you always know what you'll spend.
Most Veo 3.1 videos are ready in about 2 minutes. Times can vary with tier, resolution, duration and server load.
Yes. Every Veo 3.1 clip includes native, synchronized audio — dialogue, ambience, music and sound effects. To make characters speak, write their lines in quotes in your prompt.
Veo 3.1 outputs 720p, 1080p or 4K video in 16:9 (landscape) or 9:16 (portrait), so you can create for YouTube, TikTok, Instagram Reels and widescreen projects alike.
Yes. Image-to-video animates a start frame with an optional end frame, while reference-to-video uses 1–3 reference images to keep characters or products consistent. Reference-to-video always produces 8-second clips and is available on the Lite and Fast tiers.
Can't find what you're looking for? Contact our support team