NewSeedance 2.5just landed. A full 30 seconds, with sound, in one take.30 seconds, with sound, one take.Try it immediatelyTry it

Google · Clips · premium

Veo 3.1

Google's flagship: generates dialogue and sound from the same prompt as the picture.

What it costs

5s · silent83.5 credits
5s · with audio167 credits

What it takes

Aspect ratios16:9 9:16
Resolutions720p 1080p
Duration4, 6, 8 seconds
Reference images3
Last frameAccepted

When to reach for it

The model to use when a line of dialogue is the point. Veo writes its own audio from the same prompt that produces the image: speech, room tone, footsteps, sometimes score. Quoting a line verbatim in the prompt gets you that line rather than a mouth moving around approximate syllables.

Sound is a price switch, not a post-process. A five-second take is 83.5 credits silent and 167 with audio. That is worth it for a spoken line and rarely worth it for a landscape, so decide per shot rather than leaving it on.

Three reference images, the tightest of the models that take any, plus a last-frame slot, which is the real mechanism for continuity: render a shot, take its final frame, open the next take with it. Two aspect ratios only, 16:9 and 9:16, so a square or 4:5 deliverable has to be cropped. The Fast and Lite variants drop references entirely, which is the thing to check before planning a sequence around them.

Made with it

Compared with

Guides that cover it

Veo 3.1 is one pick in the composer.

Every model in this catalog runs from the same prompt bar, priced in the same credits. New accounts start with some to spend.

Start picturing