Google Veo 3.1 text-to-video is a premium cinematic video generator. Describe the scene and receive a high-quality short clip with smooth motion and realistic physics. You can also upload one PNG or JPG image as the first-frame reference (image-to-video): for example, upload a product photo and describe a slow orbiting camera move, and the video will evolve from that picture; only one reference image is used per run. Generation takes about one to three minutes depending on server load. Ideal for ad concepts, film storyboards, product teasers, and high-polish social posts. For specific camera work, add film terms such as dolly zoom, aerial shot, or slow motion to your description. Generated videos are 8 seconds long at 720P in 16:9 landscape. Maximum total upload size per request: 256MB (all files and message content combined). Accepted image formats: jpeg, jpg, png. Maximum size per image: 14MB. Image dimensions: at least 300 pixels per side. Maximum image resolution: 36,000,000 pixels in total. Output content formats: Video Video output: one 8-second 720P MP4 video (16:9). This module does not support continuous conversations. AI can make mistakes. Please verify important information.