> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gengen.farm/llms.txt
> Use this file to discover all available pages before exploring further.

# Gemini Omni Flash (Preview)

> Google native video generation and editing with synchronized audio.

Generate one video per task with native audio. Usage includes input, text/reasoning and video output tokens.

Omni 1.1 supports first/last frames, reference images and videos, and extension. Both models support text-to-video and video editing.

Inputs accept HTTPS URLs or caller-authorized GCS objects. Output links can be refreshed by retrieving the task during seven-day retention.

## Model ID

```text theme={"dark"}
gemini-omni-flash-preview
```

Pass this exact public ID in the top-level `model` field.

## Supported modes

* `text_to_video`
* `video_modify`

## Inputs

* `Text`
* `Image`
* `Video`

## Outputs

* `Video`

## Capabilities

* Not specified

### Additional capabilities

* `Video generation`
* `Video editing`
* `Native audio`

## Technical details

| Property | Value |
| - | - |
| Model family | `Google` |
| Modality | `video` |
| Processing | `Asynchronous task` |
| Endpoint | `/api/gengen/v1/contents/generations/tasks` |
| Durations | `3, 4, 5, 6, 7, 8, 9, 10` |
| Resolutions | `720p` |
| Aspect ratios | `16:9, 9:16` |
| Audio generation | `Supported` |
| Watermark control | `Not supported` |

<Note>
  Availability and final customer prices can change. Check the [Dashboard model catalog](https://gengen.farm/dashboard?section=models) before production use.
</Note>

See the [Omni API guide](/api-reference/google/omni-video-generation) for examples, supported modes, media limits and billing. Retrieve results with the [shared task endpoint](/api-reference/google/omni-retrieve-task).

See the [API reference overview](/api-reference/introduction) for authentication, request conventions, and response schemas.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.