Google launches Flow, its most cinematic AI video tool yet, powered by Veo 3

May 20, 2025 — Google has launched Flow, an AI filmmaking tool built for creators using its most advanced models: Veo 3, Imagen, and Gemini.

Flow lets users generate cinematic scenes using plain language, drag-and-drop ingredients, and precise camera controls. Veo 3 powers the visuals with realism and physics accuracy. Imagen handles text-to-image assets. Gemini interprets prompts clearly, turning descriptions into detailed visual outputs.

Creators can build scenes, reuse assets across clips, and shape consistent character-driven narratives. A feature called Scenebuilder allows them to expand scenes with fluid motion. Flow also includes asset management and Flow TV — a showcase of AI-generated clips that includes prompts used, so others can learn by example.

Also read: Google I/O 2025: Top 10 Highlights of Google’s New Announcements

Google developed Flow by working closely with filmmakers like Dave Clark, Henry Daubrez, and Junie Lau. Their short films — built partly with Flow — explore everything from cyberpunk worlds to personal multiverse stories.

Flow evolves Google’s earlier VideoFX project. Starting today, it’s available to U.S. subscribers of Google AI Pro and Ultra. Ultra users also get early access to native audio tools, adding dialogue and environmental sound to clips.

In other headlines, Google also recently held its I/O event with several new announcements. You can read about them here.

• Google I/O 2025: Top 10 Highlights of Google’s New Announcements
• Wear OS 6 Is Launched For Devs, Here’s What’s New in Google’s Smartwatch OS