Veo 3 is a Google video generation model from 2025 that creates sound along with the picture from a text prompt.
In plain words
Veo 3 was announced at Google I/O in May 2025. It generates the audio at the same time as the video, so a clip comes with its own soundtrack. It first reached Gemini app subscribers and Google Cloud customers, then became generally available in the Gemini API in September 2025.
A quick example
Imagine prompting for a busy street market at dusk with a vendor calling out prices. Veo 3 returns a short clip where you see the scene and hear the vendor and the crowd.
Where you'll meet it
- The Gemini app and Google Cloud's Vertex AI, at launch.
- The Gemini API, generally available from September 2025.
Related
Sources
- DocsGoogle I/O 2025: all our announcements, Google · read 29 Sept 2026
- DocsGemini API release notes, Google · read 5 Nov 2026
- DocsGenerate videos with Veo 3.1, Gemini API docs · read 2 Nov 2026
Checked by WhatIsAI against the sources above · 5 Nov 2026. Spotted an error? Report it.