Veo 3 AI video model
Google’s flagship Veo 3 model with native audio, 720p/1080p output, and optional image conditioning.
- Text / Image input support in one dashboard
- 16-32 credits depending on length
- Supports native audio
Model overview
Vidyu support for Veo 3
This page lists the model's supported inputs, output ranges, and available controls in Vidyu.
Typical use
Google’s flagship Veo 3 model with native audio, 720p/1080p output, and optional image conditioning.
Output range
4 to 8 sec output with 720p to 1080p resolution options.
Notes
Generation. Supports native audio. No required reference input.
Key controls
The main controls exposed for Veo 3
These are the model-specific controls currently available in Vidyu.
Length
4, 6, or 8 second outputs.
Resolution
1080p costs more than 720p.
Aspect Ratio
Landscape or vertical output.
Generate Audio
Adds synchronized native audio to the shot.
Negative Prompt
Optional. Helps suppress unwanted objects, styles, or motion.
Alternatives
Related models to compare
These are nearby options if you want to compare a similar setup before choosing a model.
Runway
Gen4 Aleph
Runway’s video-first generation and transformation model built around prompt-plus-video inputs.
xAI
Grok Imagine
Text-to-video and image-to-video generation with synchronized audio.
Hailuo
Hailuo 02
Physics-focused text-to-video and image-to-video with simple 6s/10s presets.
Simple Pricing
Pay for what you make. 1 credit = 1 second of video. Start at $20/month or go bigger. Cancel anytime.
One Plan
Start at $20/month for 100 credits (= 100 seconds of video). Need more? Go up to 6,000 credits. Change anytime.
- Make videos from text or images
- Download instantly, and they're yours to keep
- Change your plan anytime
- No contracts or commitments
- Cancel whenever you want
FAQ
Common questions about Veo 3
Ready to Make Your First Video?
Sign in with Google and you’ll be making videos in the next 5 minutes. Seriously, it’s that easy.