> ## Documentation Index
> Fetch the complete documentation index at: https://docs.unifically.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Gemini Omni Flash Video
> Generate videos with Google's Gemini Omni Flash video model
Generate short text-to-video, start-frame, and reference-to-video clips with Google's Gemini Omni Flash video model.
## Model
```text theme={null}
google/gemini-omni-flash-video
```
## Parameters
| Parameter | Type | Required | Default | Description |
| ---------------------- | --------- | -------- | -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `prompt` | string | Yes | - | Main video prompt. Use `@ImageN` or `@CharacterN` to point at specific references. Unknown references are left as plain text. |
| `seed` | integer | No | Random | Seed sent to Gemini Omni Flash. If omitted, a seed is generated automatically and returned when available. |
| `aspect_ratio` | string | No | `"16:9"` | Output orientation. Allowed: `"16:9"`, `"9:16"`. |
| `duration` | integer | No | `4` | Clip length in seconds. Allowed: `4`, `6`, `8`, `10`. |
| `start_image_url` | string | No | - | Publicly reachable image URL used as the first frame. Cannot be combined with `reference_image_urls` or `reference_characters`. |
| `reference_image_urls` | string\[] | No | - | Publicly reachable image reference URLs. Max 7 total expanded image + character image URLs. Cannot be combined with start/end frame fields. |
| `reference_characters` | array | No | - | Character references. Max 3 character items; expanded character image URLs count toward the total 7 reference limit. |
| `voice` | string | No | - | Request-level Google Flow voice preset ID. Requires at least one image or character reference. See [available voices](/api-reference/resources#get-google-veo-voices). |
| `allow_audio_filtered` | boolean | No | `false` | When `true`, the generation runs without audio instead of failing when the audio track is filtered. |
Start/end frame support is now available for Gemini Omni Flash video generation. For now, only start frame control (`start_image_url`) is available — end frame support is not yet available on Google's end, but it's coming in an upcoming Google update. We'll keep you posted!
Start-frame mode and reference mode are separate generation modes. Do not combine `start_image_url` with `reference_image_urls` or `reference_characters`.
## Character References
Each character must be an object with `image_urls`. Even one-image characters must use an array.
```json theme={null}
{
"image_urls": [
"https://example.com/character-front.png",
"https://example.com/character-profile.png"
],
"name": "Ada",
"description": "warm, sharp, curious"
}
```
| Field | Type | Required | Description |
| ------------- | --------- | -------- | -------------------------------------------------------------------------------- |
| `image_urls` | string\[] | Yes\* | Publicly reachable character image URLs. Use 1-10 images for a character entity. |
| `name` | string | No | Display name for the character. |
| `description` | string | No | Character notes/personality text. |
\*`image_urls` must contain at least one URL.
## Example — Reference-to-Video
```bash theme={null}
curl -X POST https://api.unifically.com/v1/tasks \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "google/gemini-omni-flash-video",
"input": {
"prompt": "Make @Character1 and @Image1 dance in a neon studio with energetic camera movement.",
"reference_image_urls": [
"https://example.com/neon-studio.png"
],
"reference_characters": [
{
"image_urls": [
"https://example.com/dancer.png"
],
"name": "Dancer"
}
],
"duration": 10,
"aspect_ratio": "9:16"
}
}'
```
## Example — Start Frame
Use `start_image_url` to anchor the first frame of the generated clip.
```bash theme={null}
curl -X POST https://api.unifically.com/v1/tasks \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "google/gemini-omni-flash-video",
"input": {
"prompt": "Camera slowly pans across the scene as clouds drift overhead",
"start_image_url": "https://example.com/start.jpg",
"aspect_ratio": "16:9",
"duration": 6
}
}'
```
## Prompt References
| Token | Refers to |
| ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
| `@Image1`, `@Image2` | Items from `reference_image_urls` only |
| `@Character1`, `@Character2` | Items from `reference_characters` only. With multiple `image_urls`, the token points to the character item; extra images are identity references |
## Rejected Combinations
| Input | Why rejected |
| ----------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
| `end_image_url` | End frame support is not yet available on Google's end. Use Veo 3.1 for first-and-last-frame workflows until Google enables it. |
| `start_image_url` with `reference_image_urls` or `reference_characters` | Start-frame mode and reference mode are separate generation modes. |
| More than 7 total expanded image URLs | Gemini Omni Flash generation reference limit. |
| More than 3 character items | Character item limit. |
| `image_url` on a character | Use `image_urls` instead, even for one image. |
| Plain string character entries | Character entries must be objects with `image_urls`. |
| Empty `image_urls` | A character needs at least one image. |
| More than 10 `image_urls` on one character | Character entity image limit. |
## Response
```json theme={null}
{
"code": 200,
"success": true,
"data": {
"task_id": "abc123def456",
"status": "pending"
}
}
```