Veo is a family of video generation models made by Google DeepMind. A video generation model is a neural network that produces a video clip from a text prompt and, optionally, from reference images. Veo 3.1, the current line, generates the audio together with the picture: sound effects, ambient noise and dialogue.
Veo 3.1 supports text to video, image to video, and video between a given first and last frame; it can also extend a video and use reference images of assets. Clips are 4, 6 or 8 seconds long at 24 frames per second, in 16:9 or 9:16, at 720p, 1080p or (for the main model) 4K, and come as MP4 files. One prompt can return up to 4 videos. People use Veo in the Gemini app and in Google Flow. Developers call Veo 3.1 and its Fast and Lite variants through Google Cloud's Gemini Enterprise Agent Platform, formerly Vertex AI; the Veo 3.1 preview in the separate Gemini API was shut down on 22 October 2026.
On Google Cloud, Veo is billed per use, with prices that depend on the variant, the resolution and whether audio is generated.