Landscape
Coastline drone shot at sunrise
Waves on black rocks with seabirds and surf in the soundtrack. Fast, 720p.
Veo 3.1 Fast · 720P · 16:9 · 8s
Use this exampleGOOGLE · VEO 3.1
Veo 3.1 8-second clips with sound, from text or frames, up to 4K
Veo 3.1 is Google's video model that generates sound with the picture — dialogue, effects and ambience. Pick Fast for most work, Lite for the lowest price or Quality for finished shots, all priced per clip.
- Native audio in every clip
- Three tiers on one page
- 720p / 1080p / 4K
Review results, manage assets and access generation history in AI Studio.
Real Veo 3.1 examples
Every example below was actually generated with Veo 3.1 on ImgAI, with the original prompt and settings. Click "Use this example" to load it into the creator.
Lifestyle
Night market wok, vertical
Flames and sizzling with crowd chatter, 9:16 at 1080p. Fast.
Veo 3.1 Fast · 1080P · 9:16 · 8s
Use this exampleAmbience
Rain on a window
A calm ambient clip with soft rain sound, made with Lite at 720p.
Veo 3.1 Lite · 720P · 16:9 · 8s
Use this exampleStory
Barista with a line of dialogue
The spoken line from the prompt is voiced in the clip. Quality, 1080p.
Veo 3.1 Quality · 1080P · 16:9 · 8s
Use this exampleWhat is Veo 3.1?
Veo 3.1 is Google's video generation model. Google highlights native audio generation together with the video, plus image-based direction: you can start from a first frame, or set both the first and last frame and let the model fill in the motion between them. Spoken lines written in quotes in the prompt can be voiced in the clip.
ImgAI offers three tiers. All make 8-second clips with sound at 720p, 1080p or 4K in 16:9 or 9:16. Fast supports text, a first frame, first and last frames or reference images; Lite is text-to-video only; Quality supports text and first/last frames. A clip costs 100–2150 credits depending on tier and resolution, and 720p and 1080p cost the same.
What Veo 3.1 is good for
Based on the model's published capabilities and what we actually generated, to help you judge whether it fits your task.
Short ads and social clips
Vertical 9:16 clips with sound, ready for Reels, Shorts and TikTok.
Dialogue scenes
Characters speaking lines you write in quotes, with natural room sound.
Product and travel B-roll
Drone shots, close-ups and street scenes with matching ambience.
Storyboard to motion
Set the first and last frames from your storyboard and let Veo animate the move between them.
Which tier to choose
The tiers in this series share one page — switch between them in the creator's model menu.
Veo 3.1 Fast
The main tier: best value, with text, first frame, first and last frames or reference images.
Veo 3.1 Lite
The lowest price. Text-to-video only — good for testing ideas.
Veo 3.1 Quality
The highest image quality for final shots. Text or first and last frames.
Veo 3.1 specs and pricing
Specs come from the configuration currently available on this site; the creator always shows the live price. Failed generations are refunded automatically.
| Veo 3.1 Fast | Veo 3.1 Lite | Veo 3.1 Quality | |
|---|---|---|---|
| Input | Text + up to 3 reference images | Text prompt only | Text + up to 2 reference images |
| Resolution | 720P · 1080P · 4K | 720P · 1080P · 4K | 720P · 1080P · 4K |
| Duration | 8 s | 8 s | 8 s |
| Prompt length limit | 4,000 characters | 4,000 characters | 4,000 characters |
Supported aspect ratios
- 16:9
- 9:16
| Tier | 720P | 1080P | 4K |
|---|---|---|---|
| Veo 3.1 Fast | 200 | 200 | 920 |
| Veo 3.1 Lite | 100 | 100 | 820 |
| Veo 3.1 Quality | 1430 | 1430 | 2150 |
Veo 3.1 prompt tips
These come from real generations — read them alongside the original prompts in the examples.
Put dialogue in quotes
Write who speaks and what they say: the barista says, "Your usual, on the house today."
Describe the sound layer
Add ambience and effects at the end of the prompt: "seabirds calling, wind and surf".
Pick 1080p over 720p
The two cost the same per clip, so choose 1080p unless you need a smaller file.
Draft on Lite or Fast, finish on Quality
Test the idea on a cheaper tier, then run the final prompt on Quality.
Veo 3.1 FAQ
Veo 3.1 is Google's video generation model that creates video with native audio. ImgAI offers it in three tiers — Fast, Lite and Quality — for 8-second clips up to 4K.
Fast for most work, with the most input options. Lite for the lowest cost when text-to-video is enough. Quality for final shots where image quality matters most.
100–2150 credits per 8-second clip on ImgAI, depending on tier and resolution. 720p and 1080p cost the same; 4K costs more. Failed generations are refunded automatically.
Yes. Every clip includes sound generated with the picture: ambience, effects and spoken lines written in quotes.
Yes, with Fast and Quality. Upload a first frame, or a first and a last frame, and describe the motion in between. Lite is text-only.
ImgAI currently offers Veo 3.1 as fixed 8-second clips, priced per clip. For other durations, see Seedance 2.0 or MiniMax H3.
Create with Veo 3.1 now
Sign up and generate with credits. Results are saved to your library, ready to download or keep editing.