Gemini OmniSpeak it. See it. Share it.

Gemini Omni makes creating videos as easy as having a conversation. Think of it like Nano Banana for video. Start from scratch, remix your gallery, or try out a premade template.

Not on a paid plan yet? Upgrade to unlock access to Gemini Omni and more.

A cinematic still generated with Gemini OmniGemini Omni

Create anything. From everything.

Blend text, images, and video to bring your ideas to life in motion.

A golden retriever puppy running through shallow water at sunset
A street dancer mid-move in a neon-lit alley at night
A chef plating a dish in a dark restaurant kitchen
A skateboarder mid-air at golden hour
A hummingbird hovering beside tropical flowers
Pour-over coffee brewing in a sunlit cafe

From concept to clip.

Gemini Omni is your creative partner for multimodal content creation.

New

Extend the scene.

Ask Gemini what happens next to lengthen your video while maintaining the story.

Extend the scene.

Keep the soul of the shot.

Swap the background, change the wardrobe, or transfer styles all while keeping your details.

Keep the soul of the shot.

Instant inspiration.

Don't wait for a spark. Jump into curated styles to see what's possible in a single tap.

Instant inspiration.

Easy editing.

Just tell Gemini what to fix. Swap characters, adjust lighting, stabilize the video, or modify the background with a chat.

Easy editing.
Anime style hill at sunrise
Stop-motion clay astronaut on a miniature planet
Vintage 8mm family picnic in a sunny park

Be the star of your own show.

Add your AI avatar to create content that looks and sounds like you. No need to upload your image every time.

An AI avatar generated with Gemini Omni

Say hello to Gemini Omni.

We’re constantly improving our models and looking for ways to make your creative process easier and more intuitive. Gemini Omni will replace Veo in the Gemini app. Omni combines Gemini's core intelligence with advanced generative media capabilities, including image to video, and video to video AI editing. It understands the world, blends different types of media, and gives you more control over editing. Create with Omni for all your AI video generation and editing needs.

Gemini Omni 1.1 Flash

Multimodal AI video generation and editing model that will now replace the previous Google Gemini Veo 3.1 model.

  • Create 10 second videos
  • Native audio generation
  • Turn photos into a video (up to 5)
  • NewScene extensions
  • NewVideo to video editing
  • NewMulti-turn editing
  • NewAvatar

Google AI subscription required. Features vary by tier and geography. 18+.

Frequently asked questions

Gemini Omni 1.1 Flash is a model that understands the world around you so you can animate photos, or create video from any input. Built on Gemini's world understanding and native multimodality, Gemini Omni creates outputs that reflect the logic of the real world and lets you shape them step-by-step through natural conversation. You can become an AI video editor with just a prompt.

What you can do with Gemini Omni:

  • Turn any combination of text, photos, or video into video
  • Create videos from photo references (up to 5)
  • Easily edit videos
  • Extend scenes to keep the story going