Veo 3.1 Standard

What it does

Veo 3.1 Standard turns a text prompt into video, and can also animate a still image you supply as a reference. Output carries native synchronized audio rather than arriving silent, and clips run up to eight seconds. On Pipe2 it renders at 720p, 1080p or 4K in the Video Generator, and that pipeline offers 16:9, 9:16, 1:1, 4:3, 3:4 and 21:9, so vertical and ultrawide deliverables are available as framing options rather than an afterthought.

When to use it

• Running the Video Generator pipeline for cinematic shots where camera motion and lighting carry the result, and you want the top Veo tier.
• Product reveals that need the on-screen action and the audio to land together, since this model produces native audio with the video.
• Lifestyle and social ads where you need the same idea delivered in more than one aspect ratio, including 9:16 and 21:9.
• Image-to-video work: you have a still you want motion built from, instead of a fresh interpretation of a text prompt alone.
• Final renders rather than exploration, where a 1080p or 4K master is the actual deliverable.

What to know before you run it

Resolution is a billing dimension: on Pipe2 this model is metered in eight-second units at 720p, 1080p and 4K, so pick the resolution you will actually ship and check the price shown in the app before you run. A reference image is optional (text-to-video works with a prompt alone), and image-to-video is the path when you already have the visual you want animated. Veo 3.1 Standard is the top Veo tier described in our catalog; other tiers are listed alongside it in the Video Generator if you want something lighter. The pipeline's duration menu goes beyond eight seconds; those longer lengths are outside what this model produces, which tops out at eight.

Also known as

Listed as Veo 3.1 or Google Veo 3.1, and identified in API contexts as veo-3.1-generate-001 or veo-3.1-generate-preview. On Pipe2 these all refer to this same Standard tier, served through the Gemini provider.