Veo 3.1 AI Video Generator
Google's high-fidelity video model with sound generated in the same pass — pick the Fast tier for iteration or Pro for maximum quality.
Veo 3.1 is Google's high-fidelity video generation model, and its signature capability is native audio: dialogue ambience, effects, and sound that are generated together with the picture, already in sync. On AutoDirector you get both tiers — Veo 3.1 Fast for quick, affordable iteration and Veo 3.1 Pro for maximum visual quality and prompt control — from the same generator, without a separate Google account.
Both tiers support text to video and image to video. Clips run 4, 6, or 8 seconds in landscape or vertical, with output from 720P/1080P up to 4K. The result reads as finished footage rather than a silent draft: for talking-style clips, atmospheric scenes, and anything where sound sells the shot, Veo 3.1 saves an entire post-production step.
A practical workflow: audition ideas on Fast at 720P/1080P (from 16 credits for a 4-second clip), then re-render the keeper on Pro or in 4K. Because both tiers share prompting behavior, the upgrade path costs no rework.
Veo 3.1 at a glance
| Tiers | Veo 3.1 Fast · Veo 3.1 Pro |
|---|---|
| Generation modes | Text to video · Image to video |
| Duration | 4 / 6 / 8 seconds |
| Resolutions | 720P/1080P · 4K |
| Aspect ratios | 16:9, 9:16 |
| Audio | Native synchronized audio (optional) |
| Pricing | Fast from 16 credits · Pro from 36 credits (4s) |
Why creators pick Veo 3.1
Native synchronized audio
Sound is generated with the picture — ambience, effects, and speech-like audio land in sync without an editing pass.
Two tiers, one workflow
Fast for cheap iteration, Pro for maximum fidelity. Same prompts, same parameters — switch tiers without rewriting anything.
4K output
Both tiers offer a 4K option for final delivery, with 720P/1080P as the standard working resolution.
High visual fidelity
Sharp detail, stable subjects, and consistent lighting — Veo 3.1 output holds up on large screens.
Image to video
Animate stills with audio in one step — product photos and key art become finished, sounding clips.
Predictable per-clip pricing
Priced per clip by tier and duration, shown before you submit — no surprises on longer renders.
How to generate with Veo 3.1
- 1
Open the generator
Go to the Text to Video tool and choose Veo 3.1 Fast or Pro from the model list — or start from Image to Video with a still.
- 2
Describe scene and sound
Alongside subject and camera, mention the audio you want — rain, crowd murmur, engine roar. Veo 3.1 renders it with the picture.
- 3
Pick duration and resolution
Choose 4, 6, or 8 seconds, landscape or vertical, and a quality tier. The credit estimate updates before you submit.
- 4
Iterate on Fast, finish on Pro
Explore variations cheaply on Fast, then re-render the winning prompt on Pro or in 4K for delivery.
Veo 3.1 prompt examples
Mention sound explicitly — audio direction is what sets Veo 3.1 prompts apart.
Atmosphere with audio
A cozy cabin interior during a thunderstorm, rain drumming on windows, distant thunder, fireplace crackling, camera slowly pushes toward the window, warm interior light against blue storm light
Product with sound design
An espresso machine pulls a shot in extreme close-up, steam hissing, cup clinking on saucer, rich crema swirling, bright modern kitchen, shallow depth of field, commercial style
Vertical street energy
Vertical video: skateboarder lands a trick in a graffiti-covered underpass, wheels rolling on concrete, board snap echoing, golden hour light shafts, handheld camera whip-pans to follow
Veo 3.1 pricing
Veo 3.1 Fast: a 4-second 720P/1080P clip is 16 credits without audio, 24 with audio; 4K from 48.
Veo 3.1 Pro: a 4-second 720P/1080P clip is 36 credits without audio, 72 with audio; 4K from 72.
6-second clips cost 1.5× the 4-second price; 8-second clips cost 2×.
See credit packs and plansVeo 3.1 FAQ
What's the difference between Veo 3.1 Fast and Pro?
Fast is tuned for speed and cost — ideal for iteration. Pro produces the highest visual fidelity and the strongest prompt control. They share modes and parameters, so prompts transfer directly between tiers.
Does Veo 3.1 really generate audio?
Yes. Audio is generated in the same pass as the video and arrives synchronized — ambience, effects, and speech-like sound. You can also generate without audio at a lower credit cost.
How long can Veo 3.1 videos be?
4, 6, or 8 seconds per generation, in 16:9 or 9:16. For longer sequences, generate consecutive shots and edit them together.
How much does Veo 3.1 cost?
Fast starts at 16 credits for a 4-second clip and Pro at 36, with audio and 4K adding to the price. Exact cost shows in the generator before you submit, and failed generations from system errors are refunded automatically.
Can I use Veo 3.1 videos commercially?
Yes. Videos you generate on AutoDirector are yours to use in marketing, social media, ads, and commercial projects.
Veo 3.1 or Seedance 2.0 — which should I pick?
Pick Veo 3.1 when built-in audio or maximum fidelity in short clips matters most. Pick Seedance 2.0 for longer durations (up to 15s), reference to video, and more aspect ratios.
Compare with other models
Direct your first Veo 3.1 clip
Picture and sound in one pass — iterate on Fast, deliver on Pro.