Gemini Omni AI Video Generator

Multimodal video generation from text, images, and reference video.

Text to videoImage to videoReference to videoVideo to video

Create with Gemini Omni View API

OmniGO

Ready to create

Selected model

Gemini Omni

Default resolution

720p

Default ratio

16:9

Model capabilities

What Gemini Omni can do

Duration

5–15 seconds

Resolution

720p

Aspect ratio

16:9 · 9:16 · 1:1

Reference media

7 images · 1 videos

Native audio

Not supported

Generation controls

Supported parameters

Tavoa adapts these controls to Gemini Omni and sends only the fields supported by its Kie route.

Prompt: Describe the subject, motion, camera, lighting, and style
Input modes: Text to video · Image to video · Reference to video · Video to video
Duration: 5–15 seconds
Resolution: 720p
Aspect ratio: 16:9 · 9:16 · 1:1
Reference media: 7 images · 1 videos

Gemini Omni, powered through Kie API

Tavoa submits an asynchronous Kie generation task, stores the provider task ID, and polls the compatible record endpoint until the video succeeds or fails. Your Kie key remains server-side.

Provider: Kie.aiAsynchronous task workflow

Tavoa API

Create task

POST /api/v1/videos

Query task

GET /api/v1/videos/:taskId

Kie model ID

gemini-omni-video

Tavoa catalog ID

gemini-omni

Make your next video with Gemini Omni

Open the studio with this model selected, add your prompt or reference media, and start generating.

Create with Gemini Omni