Gemini Omni 1.2 Flash
Text & image to video
The current Gemini Omni. Clips up to 15 seconds with native audio, from text or images, plus editing of existing videos up to 15 seconds by plain-language instructions.
AI video model · By Google DeepMind
Google's conversational video model in your Qten account: make a clip, then change it by describing what you want.
Free plan · No credit card · Updated 2026-11-18
Gemini Omni
By Google DeepMind
The current Gemini Omni release, in your Qten account.
Gemini Omni is Google's conversational AI video model. It generates clips with native sound from text or images and edits existing videos when you describe the change, much like Nano Banana does for images. Qten offers Gemini Omni 1.2 Flash, which makes clips of up to 15 seconds.
Gemini Omni comes from Google DeepMind and is built on the Gemini family, so you work with it the way you would with a chat assistant: generate a clip, then ask for changes such as a different season, a new outfit or another camera angle. The first Omni Flash preview made clips of up to 10 seconds; version 1.2 Flash raises that to 15 seconds and can edit or extend existing video. Audio is generated together with the picture.
| Made by | Google DeepMind |
|---|---|
| Newest on Qten | Gemini Omni 1.2 Flash |
| Versions on Qten | 1 |
| Max length | Up to 15 s |
| Native audio | Yes |
| Inputs | Text prompt · Start image · Video editing |
Limits are the maker's published figures, checked 2026-11-18. What you can use may depend on your plan.
The current Gemini Omni release, in your Qten account.
Text & image to video
The current Gemini Omni. Clips up to 15 seconds with native audio, from text or images, plus editing of existing videos up to 15 seconds by plain-language instructions.
| Version | What it makes | Tier | Released |
|---|---|---|---|
| Gemini Omni 1.2 Flash | Text & image to video | Standard | — |
Change the weather, the outfit or the scene of a clip without starting over.
Dialogue, effects and ambience are generated with the video.
Longer clips than the first Omni preview, in one generation.
Start from a prompt or animate one of your images.
A golden retriever in a yellow raincoat splashes through puddles on a city street, kids laughing in the background, rain sounds, handheld camera, 9:16.Edit this clip: change the season to winter, add gentle snowfall and frost on the windows, keep the people and camera movement the same.A street food vendor flips a giant pancake into the air and catches it, the crowd cheers, sizzling sounds, slow motion at the catch, 16:9.Adjust one detail instead of regenerating the whole shot.
Short clips with sound for Reels, Shorts and TikTok.
Turn one clip into several versions for testing.
Bring stills and thumbnails to life.
The other video models in the same Qten account. Pick per scene, or let Qten choose.
| Gemini Omni | Veo | Kling | Seedance | Grok Imagine | |
|---|---|---|---|---|---|
| Made by | Google DeepMind | Google DeepMind | Kuaishou | ByteDance | xAI |
| Newest on Qten | Gemini Omni 1.2 Flash | Veo 3.1 | Kling 4 | Seedance 2.5 | Grok Imagine Video 1.5 |
| Versions on Qten | 1 | 2 | 6 | 7 | 3 |
| Max resolution | — | Up to 1080p | Up to 1080p | Up to 1080p | Up to 1080p |
| Max length | Up to 15 s | Up to 8 s | Up to 30 s (Kling 4) | Up to 30 s (Seedance 2.5) | Up to 15 s (Video 1.5) |
| Native audio | Yes | Yes | Yes | Yes (Seedance 2.0 / 2.5) | Yes |
| Inputs | Text prompt · Start image · Video editing | Text prompt · Start image · First & last frame · Reference images | Text prompt · Start image · First & last frame · Reference images | Text prompt · Start image · Reference images · Audio | Text prompt · Start image · First & last frame · Reference images |
Limits are the maker's published figures, checked 2026-11-18. What you can use may depend on your plan.
Sign up on the Free plan. No credit card, and you get credits to start.
Write your prompt or script, then choose Gemini Omni as the model, or let Qten pick the best model for each step.
Review the result, edit it in Qten, and post or schedule it to YouTube, TikTok, Instagram and more.
FAQ
Gemini Omni is Google DeepMind's conversational AI video model. It generates video with sound from text or images and edits existing clips from plain-language instructions.
Qten offers Gemini Omni 1.2 Flash, the current version.
Qten has a Free plan with 100 free credits and no credit card. Generating with Gemini Omni uses credits, depending on the clip length and settings. See the Pricing page for details.
Gemini Omni 1.2 Flash makes clips of up to 15 seconds and can edit input videos of up to 15 seconds.
Veo 3.1 is Google's model for polished, cinematic shots. Gemini Omni is built for conversational generation and editing, where you refine a clip step by step. Both are in Qten.
No. You use Gemini Omni from your Qten account with Qten credits, without a Google subscription or API key.
Model names and logos are trademarks of their owners. Qten is not affiliated with or endorsed by them.
Gemini Omni and 130+ other AI models in one account. Start free.
Start creating free