Veo 3.1
Google Veo 3.1 text-to-video and image-to-video with native audio, 8-second clips at 720p or 1080p.
At a glance
- Starting price
- 7,500 credits
- Type
- Text-to-video, image-to-video
- Duration
- 8 seconds (fixed)
- Resolution
- 720p or 1080p
- Aspect ratio
- 16:9 and 9:16 on every tier
- Audio
- Yes — native synchronised audio
- Image input
- Yes — animate a still
Veo 3.1 is Google DeepMind's flagship video model and the highest-fidelity option on DubVoice.ai. It generates an 8-second clip from a text prompt, or animates a still image you upload, and it renders its own synchronised audio — dialogue, ambience and effects — rather than leaving you a silent clip to score afterwards.
The family ships in three tiers. Veo 3.1 is the full model. Veo 3.1 Fast is roughly half the cost of the full tier and is the default here, because for most social and ad work the difference is not visible at the sizes people actually watch on. Veo 3.1 Lite sits between them at 9,100 credits. All three take the same aspect ratios and the same reference images — the only thing that changes between them is fidelity and price.
Every tier is fixed at 8 seconds, and every tier renders 9:16 as well as 16:9 — so vertical for Reels, Shorts and TikTok is available at whatever quality level you are paying for. If you need longer than 8 seconds, extend the clip, generate consecutive shots and cut them together, or use Grok Imagine, which goes to 15 seconds in one pass.
Veo 3.1 pricing
| What you get | Credits | Approx. USD |
|---|---|---|
| Veo 3.1 — 8s · 720p | 17,000 | $0.14 |
| Veo 3.1 — 8s · 1080p1080p is 1.5x the 720p price across the whole family. | 25,500 | $0.21 |
| Veo 3.1 Lite — 8s · 720p | 9,100 | $0.08 |
| Veo 3.1 Fast — 8s · 720pThe default tier. Same 8s clip, roughly half the cost of the full model. | 7,500 | $0.06 |
USD figures use the 3,000,000-credit package at its $24.99 list price. Credits never expire and there is no subscription — the same balance covers every model on the platform. See credit packages.
What it can do
- ✓Native audio generated with the video, already in sync
- ✓Image-to-video: upload a still and direct the motion
- ✓Prompt-level control of camera moves, lighting and pacing
- ✓Extend an existing clip into a longer sequence
- ✓Vertical 9:16 output on every tier
Limitations
- —Fixed 8-second clips
- —Text rendered inside the frame is unreliable, as with every video model today
Compared with other models
Frequently asked questions
How much does one Veo 3.1 video cost?
An 8-second 720p clip costs 17,000 credits on the full Veo 3.1 tier, 9,100 on Lite and 7,500 on Fast. 1080p is 1.5x those figures. At the 3M package rate that is roughly $0.14, $0.08 and $0.06 per clip.
Does Veo 3.1 generate sound?
Yes. Veo 3.1 produces synchronised audio — dialogue, ambience and effects — as part of the same render, so the clip arrives with sound already matched to the picture.
Can Veo 3.1 make vertical 9:16 videos?
Yes, on every tier — Lite, Fast and the full model all render 9:16 natively, so vertical costs the same as landscape at the quality level you pick.
Do I need a subscription to use Veo 3.1?
No. DubVoice.ai has no subscription. You buy a credit pack once, the credits never expire, and a Veo render draws from the same balance as text-to-speech, images and music.
Alternatives on DubVoice.ai
Omni Flash
Duration-tiered video from 4 to 10 seconds, the cheapest way to produce social clips at volume.
from 2,344 credits
Grok Imagine (Video)
Fast 6, 10 or 15-second clips at 480p or 720p across five aspect ratios, priced as a flat matrix.
from 3,000 credits
Meta AI Video
Flat 2,000 credits per clip — the lowest per-clip price for AI video on the platform.
from 2,000 credits
About DubVoice.ai
DubVoice.ai is an all-in-one AI creation platform for voice, video, images, music, dubbing and translation.