Edit Videos by Talking to Google's New AI — No Code Required

I’ve been waiting for this. Not because AI video is new — tools like Runway and Sora have been around for a while — but because none of them let you just talk to the video and watch it change. Google announced Gemini Omni at I/O 2026 on May 19th, and the first version, Gemini Omni Flash, is live now in the Gemini app, Google Flow, and YouTube Shorts.

Here’s the short version: Gemini Omni is a conversational video model. You give it a clip, a photo, or a text description, then tell it what to change in plain English (“swap the background to a beach,” “make it look like it was filmed in the 1970s”), and it applies each edit while keeping your characters, lighting, and objects consistent. Every video it generates carries a SynthID watermark, Google’s invisible tag for AI-generated content.

What does Gemini Omni actually do?

Most AI video tools work like a vending machine: you type a prompt, a video comes out. If you don’t like it, you start over. Gemini Omni works more like a conversation with a video editor.

You give it a video clip, a photo, or just a text description, and then you tell it what to change. “Change her shirt to blue.” “Make it look like it was filmed in the 1970s.” Each instruction builds on the last, because the model remembers what’s already in the scene and preserves it.

The first version available now is called Gemini Omni Flash. It supports:

• Video from text — describe a scene, get a short clip
• Photo animation — give it a still image, it brings it to life
• Conversational editing — change anything through chat commands
• Video-to-video editing — upload an existing clip and modify it
• AI avatars — create a digital version of yourself for content

Every video gets a SynthID watermark, which matters as deepfake concerns have grown louder through 2025 and 2026.

Why does this matter if you don’t code?

If you’re already using AI image generators or making TikTok videos on a budget, you know the problem: video is hard. Images are one frame. Video is 30 frames per second, every second, and keeping things right across all those frames is what separates a 10-second clip from a 2-hour editing session.

Gemini Omni removes the editing interface entirely. There’s no timeline to drag clips around on, no keyframes to set, no rendering queue to wait through. You talk, it adjusts. You iterate, it remembers.

I tested it with a simple scenario: I took a photo of a desk setup and told Omni to “turn this into a video of someone typing, with rain falling outside the window.” It generated a 10-second clip with consistent lighting, realistic rain physics, and natural hand movement. I couldn’t have produced that in CapCut or Descript without significant skill.

The model also handles real-world physics better than previous tools — gravity, motion, how liquids behave. AI-generated scenes look noticeably less “floaty” than what earlier models produced.

What does Gemini Omni cost?

YouTube Shorts access is free right now. The Gemini app and Google Flow require a Google AI Plus, Pro, or Ultra subscription, and a developer API is coming soon with pricing still unannounced.

If you’re already a Gemini subscriber on any paid plan, Omni Flash is live for you right now. If you’re a YouTube Shorts creator, you can start experimenting without paying anything.

The free YouTube Shorts integration is the real play here. Google wants billions of existing creators using Omni immediately — not by switching to a new app, but by working inside the tools they already use. That’s the same playbook that made Google’s AI tools sticky in other categories.

How does Gemini Omni compare to Sora and Firefly?

OpenAI Sora excels at generating entirely new video clips from a single text prompt. If your goal is “make me a video of a dog surfing in space,” Sora is probably your best bet. But it doesn’t let you iteratively edit — you generate, you’re done, and you start over if you want changes.

Adobe Firefly is built into professional tools like Premiere Pro and After Effects. If you already know those tools, Firefly is powerful. The learning curve is steep, though, and the subscription cost adds up.

Gemini Omni sits in a different lane. It’s designed for the person who has a video, a photo, or an idea and wants to improve it through conversation. The barrier to entry is literally “can you describe what you want changed?” For the beginner audience we focus on here, that’s the winning proposition. You don’t need to learn editing software or prompting frameworks. You just talk.

How do the AI avatars work?

One feature I keep coming back to: personal avatars. You create a digital version of yourself that looks and sounds like you, then generate videos starring that avatar. No filming yourself, no uploading your face every time.

For anyone building a personal brand, teaching courses, or creating social media content, this changes the production equation. You can make talking-head videos without a camera, a microphone, or even being in the same room.

Google says it has “clear policies to protect” against misuse, though the full safeguard details haven’t been released yet. Expect this feature to attract scrutiny — and expect it to be wildly popular with creators anyway.

How do I get started with Gemini Omni?

If you have a Google AI Plus, Pro, or Ultra subscription:

1. Open the Gemini app
2. Upload a photo or video, or type a description
3. Tell it what you want, in plain English
4. Iterate through the conversation until it’s right

If you don’t have a subscription, start with YouTube Shorts — the integration is free and rolling out now.

One more thing worth knowing: Omni replaces Google’s previous video tool, Veo, in the Gemini app. If you were using Veo before, you now have Omni instead, and it’s a significant upgrade.

Is Gemini Omni worth trying?

If you’ve been intimidated by video production, yes. The conversational interface is the actual breakthrough here — describe what you want, get it, refine it, done. You don’t need to learn editing software or understand video formats. You need to be able to describe what you want. That’s it.

Whether you’re building automations with Zapier, Make, or n8n, or just getting started with the tools I actually use every day, video production just got added to the “things AI can handle” list.

I made the mistakes learning video editing the hard way. You don’t have to anymore.

Ready to start building? Check out our AI Tool Advisor to find the right tools for your project.

FAQs

What is Gemini Omni? Gemini Omni is Google’s conversational AI video model, announced at I/O 2026 on May 19th. You give it a video, photo, or text description, then request changes in plain English. It applies each edit while keeping characters, lighting, and objects consistent across the whole clip, and every video carries a SynthID watermark identifying it as AI-generated.

Is Gemini Omni free? The YouTube Shorts integration is free and available now. Access through the Gemini app or Google Flow requires a Google AI Plus, Pro, or Ultra subscription. A developer API is coming soon, with pricing still unannounced.

Can Gemini Omni edit videos I already have? Yes. Video-to-video editing is one of Omni Flash’s core features: you upload an existing clip and modify it through chat commands like “change the background” or “make it look like it was filmed in the 1970s.” It also animates still photos and generates short clips from text descriptions.

How is Gemini Omni different from OpenAI’s Sora? Sora is strongest at generating entirely new clips from a single prompt, but it doesn’t support iterative editing — if you want changes, you regenerate from scratch. Gemini Omni is built around conversation: each instruction builds on the last, and the model preserves what’s already in the scene.

What happened to Google Veo? Gemini Omni replaces Veo as the video tool inside the Gemini app. If you were using Veo before, you now have Omni instead, which adds conversational editing, photo animation, and AI avatars on top of text-to-video generation.