Google has released Veo 3.1 and Veo 3.1 Fast in paid preview, adding new capabilities to the generative video model that is already a leader in the field. Creative and technical upgrades include richer native audio from dialogue to sound effects, greater understanding of cinematic styles and better prompt adherence. The two new models are available via the Gemini API in Google AI Studio and Vertex AI, with Veo 3.1 also available in the Gemini app and the storytelling tool Flow, which now gets native audio. Flow has generated more than 275 million videos since its release at Google I/O in May, according to the company.

According to a Google blog post, Flow now features enhanced editing functions for “more granular control” over the final scene as well as in-app audio generation for tools including Ingredients to Video (which combines up to three reference images), Frames to Video (transforming stills into video) and Extend (for lengthening scenes) — all powered by Veo 3.1.

Google explains the changes are the result of user requests for more artistic control and discrete audio within Flow. Google’s demo clip shows Flow and Veo 3.1 combining reference images of a location, an actress, and an outfit for a fully formed scene with dialogue and sound effects.

“The quality is higher, the physics better, the pricing the same as before, and the control and editing features more robust and varied,” VentureBeat says of Google’s GenVid improvements, pointing out that while aspiring or professional filmmakers can benefit from the online creation tool Flow, the models’ release “signals a growing opportunity for enterprises, developers, and creative teams seeking scalable, customizable video tools.”

VentureBeat suggests Veo 3.1 “delights with each generation,” but looks “a little more ‘artificial’ than” OpenAI competitor Sora 2, which “excels at handheld and ‘candid’ style videos.”

While Veo 3.1’s initial clip generation is selectable at 4 seconds, 6 seconds or a default maximum of 8 seconds, Extend can elongate that “to more than 30 seconds” or even a minute-plus “when continuing from a prior clip’s final frame,” according to VB.

Veo 3.1, which also accepts text prompts, “specializes in blending disparate images into natural-looking videos, significantly reducing the time and resources that have historically been required for video production,” ZDNet writes, noting that Amazon Ads in June debuted enhanced Video Generator features that let brands create short video from product stills “in a matter of seconds.”

Veo 3.1 has HD resolution (720p or 1080p) across all access points. A Google Cloud blog post goes a bit deeper into the capabilities on Vertex AI. Veo 3.1 Fast offers quicker rendering with less visual fidelity, good for rapid prototyping.

Curious Refuge offers reviews of both Veo 3.1 Fast and the foundation Veo 3.1.