Veo 3.1
Google's best performances, speech and sound. It is made from the written shot, so faces can change between shots.
- What it is
- Video model with sound and speech
- Made by
- Clip length
- 8 seconds
- Sound
- Its own sound, and characters can speak a line
- Starts from
- The written shot (words)
- Price
- 14 tokens a second
- Public ranking
- 28th for image to video with sound
The shot: Cold blue dusk, whitecaps crashing on black rocks, a lighthouse beam sweeping overhead. A weathered woman in her late fifties in a cream cable-knit sweater picks her way along the shore and stops, her eyes narrowing at a glint of green glass between two rocks. Slow push in. She says: “Twenty years I've kept this light. Maybe it's time it kept itself.”
What Veo 3.1 is
Veo 3.1 is Google's top video model. Characters speak their lines with natural mouth movement, and the sound of the scene comes with it.
As it runs in this studio, Veo does not accept a first frame of a realistic person, so each shot is made from its description.
Strengths and weaknesses
No model is best at everything. This is where Veo 3.1 earns its place, and where another model will serve you better.
Where it is strong
- She spoke the line in our test, with the sound of rain and sea made alongside.
- It directed the shot itself: a wide view of the shore, then a close-up of her face.
- A clip took 69 seconds to make.
Where it falls short
- Faces vary. Each shot is made from words, so the same character can look different from one shot to the next.
- One length only: 8 seconds.
- It added black cinema bars above and below the picture, which nobody asked for.
- Expensive: 14 tokens a second, so 112 tokens a clip.
- It ranks below Seedance, Wan 3.0 and Kling 3.0 Pro on the public board (28th).
Best for
- One-off shots with dialogue
- Scenes where the same actor does not have to return
Pick another model when
- The same person appears in several shotsWan 3.0 →
Where you can use it
One place in the studio runs this model. The link opens the tool; the price is shown again before anything is charged.
Compare with
Other video models in the studio, each with its own samples and notes.
Alibaba · VideoWan 3.0Natural movement with sound and speech, up to 30 seconds, from the shot's first frame. The High quality setting.4 tokens a secondSee samples
Google · VideoVeo 3.1 FastThe quicker, cheaper Veo: characters speak their lines with sound, made from the written shot.5 tokens a secondSee samples
Lightricks · VideoLTX 2.3 FastFast 720p video with sound for one token a second. The studio's default, and the best value for long films.from 6 tokensSee samples
Lightricks · VideoLTX 2.5 FastThe newer LTX: sharper detail and steadier motion than 2.3, with sound, up to 20 seconds.from 18 tokensSee samplesQuestions
Something else? Ask us.
How much does Veo 3.1 cost on ideahits?
Veo 3.1 costs 14 tokens a second (112 tokens for 8 seconds) in AI Video Studio. You pay with tokens from one balance that works on every model, and the price is shown before each run. A run that fails is refunded.
What is Veo 3.1 best for?
One-off shots with dialogue; Scenes where the same actor does not have to return. Consider Wan 3.0 when the same person appears in several shots.
Do I need an account with Google to use Veo 3.1?
No. Veo 3.1 runs inside the ideahits studio. One ideahits account and one token balance cover every model here.
Can I use what Veo 3.1 makes for commercial work?
Yes. What you make in the studio is yours to use, including in adverts, on products and for clients.
Try Veo 3.1.
Create an account, pick a pack from $6, and drop in a picture.
10 free tokens to start





