# Gemini Omni Flash 1.1

> Video AI Model by Google — available on Layer

Google's multimodal video model — 720p, 1080p, or 4K clips with synchronized native audio from text or a still image.

Gemini Omni Flash 1.1 is Google's multimodal video generation model that creates 720p, 1080p, or 4K clips with synchronized native audio from a text prompt or a still image. Built on Google's Gemini architecture, it generates 3–10 second videos in 16:9 or 9:16 with speech, sound effects, and ambient audio baked into every output. Optional last-frame control on image-to-video and prompt-driven edits on existing footage make it well-suited for social content, rapid concepting, and game cinematics.

## Specifications

| Property | Value |
|----------|-------|
| Provider | Google |
| Category | Video |
| Price | 2 / second per second |
| Aspect Ratios | 16:9, 9:16 |
| Durations | 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s |

---

[Try Gemini Omni Flash 1.1](https://layer.ai/me/session/new?baseModelId=GEMINI_OMNI_FLASH_1_1) | [All Video Models](https://layer.ai/models/video) | [All Models](https://layer.ai/models)