Veo 3.1: generate, then edit it properly

Veo 3.1 is Google’s video model, and the headline feature is native audio: it generates a soundtrack with the footage, including ambience and, in some prompts, speech.

It is the model people mean when they talk about generated video that does not immediately read as generated. The trade is a hard 8 second ceiling.

In the picker it is described as: Native audio, 8s max.

You want sound and picture generated together in one pass.

The clip is short and needs to look as convincing as the current state of the art allows.

Where it runs out: Eight seconds maximum, so it cannot carry a long shot on its own. Highest tier pricing, and 1080p or 4K output costs more than the 720p default.

Every model here runs on the same timeline, so the choice is per clip rather than per project: generate an establishing shot with one and a quick filler with another, then cut them together in the same tab.

Credit costs below are the starting cost for each model’s shortest clip. Longer durations and higher resolutions cost more.

Most generators hand you a clip and stop, which leaves you downloading files and re-uploading them somewhere else to make anything of them.

In REQO the Veo 3.1 result lands on a timeline next to your screen recordings and uploads. Trim it, stack it, caption it from the transcript, and share the finished thing with a link, without leaving the tab.

The AI Studio (talking avatars, text-to-video and AI images) and the AI clip tools (background removal, chroma key, face touch-up, noise cancellation, auto cleanup, auto b-roll, auto-zoom) are Pro features. Generation includes 100 credits a month plus top-ups.