Google offers AI-powered video generation tools that let anyone create short, cinematic video clips by typing a text description or providing reference images. The technology is available through the Flow filmmaking tool, the Gemini app, and Vertex AI for enterprises, and is powered by Google's Veo model family. By October 2025, Flow had generated over 275 million videos.

Veo was introduced at Google I/O in May 2024. Veo 2 followed in December 2024 with improved physics modeling and realism. Veo 3, released at Google I/O in May 2025, added the ability to generate synchronized audio, sound effects, and dialogue alongside video. Veo 3.1 launched in October 2025 with richer audio, stronger prompt adherence, and multi-image synthesis. A January 2026 update to Veo 3.1 added native vertical (9:16) output and 4K upscaling via Flow, the Gemini API, and Vertex AI. All outputs include an invisible SynthID watermark. Veo 3.1 is available via the Gemini app, Flow, Gemini API, Vertex AI, and Google Vids.