
Google Veo 3.1 is Google DeepMind's video generation model for turning a written scene into a short, finished clip with synchronized audio. Introduced in October 2025 as an upgrade to Veo 3, it improves prompt and camera-direction adherence while generating dialogue, ambience and sound effects in the same pass as the picture. Google's API also adds reference-image guidance, scene extension and first-to-last-frame transitions for the family. On this platform, Veo 3.1 is the standard entry point: describe one shot, choose widescreen or vertical framing, and get a clip back with native sound. It suits ads, social teasers and single-shot story beats. Clip length, resolution and available input modes are set by the runtime and shown before you submit.
Google Veo 3.1
Google動画
公開日2025年10月




