Google's new Gemini Omni turns a sentence into a video — and lets you edit it by asking. Here's what it does, plus the 3-minute version you can watch right now.

You can now make a video by typing one sentence — and then change that video just by asking for changes, the same way you'd text instructions to a designer. Google calls it Gemini Omni. The first version, Omni Flash, is live right now. The simplest way to picture it: it's Nano Banana, but for video.

Prefer to watch? We turned this whole issue into a 3-minute overview with AI:

Lindy remembers what you forgot to write down.

TLDR: Gemini Omni builds one coherent video from a mix of inputs — a sentence, a photo, a voice memo, an existing clip — then lets you refine it through plain-English conversation instead of starting over. Omni Flash is live now in the Gemini app, in Google Flow, and free on YouTube Shorts. The skill that matters now isn't editing. It's describing.

Why this one is different

For the last year, most AI video tools worked the same way. You typed a prompt, the tool handed you a clip, and if it came out wrong, your only option was to start over and try a different prompt. Gemini Omni breaks that pattern in two ways.

First, it takes a mix of inputs at once. You can give it a sentence, a photo, a voice memo, an existing video clip, or any combination of those, and it builds one coherent video that pulls from all of them. You're not describing a scene from a blank page — you're handing it raw material and direction.

Second, and this is the part that genuinely didn't exist before, you keep editing in plain English. One instruction at a time. "Make it nighttime." "Swap the car for a bicycle." "Move the camera behind her." Omni changes only that thing and leaves the rest of your video intact. No rebuilding from scratch. That conversational back-and-forth is what separates it from every tool that came before.

Where you can actually use it

Omni Flash is rolling out across the Gemini app, Google Flow, and YouTube Shorts — where it's free to try. It's included for Google AI Plus, Pro, and Ultra subscribers. For now it produces video only — image and audio output are coming in later versions. Under the hood, it pulls together Google's earlier media models, including Veo and the wildly popular Nano Banana image editor, into one system you steer by talking.

Why you should care, even if you've never made a video

You no longer need an editor, a software license, or a week of turnaround to get a short, on-brand video out of an idea. A product teaser, a quick explainer for your team, a social clip — the distance from "idea in your head" to "finished video on the screen" just collapsed into a conversation. Every clip Omni makes carries Google's invisible SynthID watermark, so it stays traceable as AI-generated.

Turn your idea into a video tonight

The hardest part isn't the tool — it's knowing what to ask it for. So we built a prompt that interviews you about your idea first, then hands you a ready-to-paste video brief, a shot-by-shot outline, and the exact plain-English edits to refine it.

The Idea-to-Video Brief →

Same prompt. Four readers. Four completely different videos:

The skill that matters now isn't editing — it's describing. If you can clearly say what you want, you can make it. So go describe something.

AI Super Simplified is where busy professionals learn to use artificial intelligence without the noise, hype, or tech-speak. Each issue unpacks one powerful idea and turns it into something you can put to work right away.

From smarter marketing to faster workflows, we show real ways to save hours, boost results, and make AI a genuine edge — not another buzzword.

Get every new issue at AISuperSimplified.com — free, fast, and focused on what actually moves the needle.