Gemini Omni Flash 1.2 Video Edit

Edit an existing uploaded video with Google’s Gemini Omni 1.2 Flash. Provide exactly one source video URL in reference_video_urls and an edit instruction. The edited window can be up to 15 seconds long (1.1 allowed 10), and edits are billed like generations, by the length of the edited window. The request body is the same as Gemini Omni Flash 1.1 Video Edit. Try it in the browser: Gemini Omni Flash 1.2 API page.

Model

google/gemini-omni-flash-1.2-video-edit

Parameters

Parameter	Type	Required	Default	Description
`reference_video_urls`	string[]	Yes	-	Publicly reachable source video URL. Must contain exactly one URL. Uploaded source videos must meet the limits below.
`prompt`	string	Yes	-	Edit instruction. Use `@Video1` to refer to the source video and `@ImageN`/`@CharacterN` for extra references.
`reference_image_urls`	string[]	No	-	Publicly reachable image URLs used as edit references. Max 5.
`reference_characters`	array	No	-	Character references for the edit. Max 3 character items. Each character may include 1-10 `image_urls` and a per-character `voice` or `custom_voice`. See available voices.
`seed`	integer	No	Random	Seed for reproducible results, `0` to `2147483647`. If omitted, a seed is generated automatically and returned when available.
`start_frame`	integer	No	`0`	First source frame index included in the edit window.
`end_frame`	integer	No	Source end	Last source frame index included in the edit window. If omitted, the service uses the detected final frame when available. The window from `start_frame` to `end_frame` can be up to 15 seconds.
`aspect_ratio`	string	No	Source shape	Output orientation. Allowed: `"16:9"`, `"9:16"`. If omitted, the output keeps the source video’s shape: a portrait source returns `"9:16"`, anything else `"16:9"`.
`resolution`	string	No	`"720p"`	Output resolution. Allowed: `"360p"`, `"720p"`, `"1080p"`, `"4k"`. `"360p"` and `"720p"` generate natively. With `"1080p"` or `"4k"`, the edited video is upscaled after generation as part of the same task.
`allow_audio_filtered`	boolean	No	`false`	When `true`, the generation runs without audio instead of failing when the audio track is filtered.
`nsfw_check`	boolean	No	`false`	Check the prompt and input images for NSFW content before generating. Off unless set to `true`

Billing

An edit costs the same as a generation of the same length at the same resolution. The length is the edited window (start_frame to end_frame), rounded up to whole seconds, with a 3 second minimum. Editing 7.2 seconds at 720p costs the same as generating an 8 second 720p clip. See current rates on the pricing page.

Limits

Limit	Value
Video references	1
Reference images	5
Character references	3
Edited window	Up to 15 seconds
Uploaded source video size	Up to 1 GB
Uploaded source video length	Up to 30 seconds

Character References

Each character must be an object with image_urls. Even one-image characters must use an array. Add a preset voice or a tuned custom_voice per character.

{
  "image_urls": [
    "https://example.com/character.png"
  ],
  "name": "Ada",
  "description": "warm, sharp, curious",
  "custom_voice": {
    "voice": "achernar",
    "name": "Ada voice",
    "voice_performance": "calm, bright, expressive",
    "sample_dialogue": "Hello, I am Ada."
  }
}

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.
`voice`	string	No	Preset voice for this character. Do not combine with `custom_voice` on the same character.
`custom_voice`	object	No	Tuned voice config: `voice` (base preset), `name`, `voice_performance`, and `sample_dialogue` (max 120 characters) are required; `speaker` is optional.

*image_urls must contain at least one URL.

Example — Edit Part of a Clip

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-1.2-video-edit",
    "input": {
      "reference_video_urls": [
        "https://example.com/source-video.mp4"
      ],
      "prompt": "Make @Video1 look like it was filmed underwater.",
      "start_frame": 0,
      "end_frame": 288,
      "resolution": "720p"
    }
  }'

Prompt References

Token	Refers to
`@Video1`	The source video
`@Image1`, `@Image2`	Items from `reference_image_urls` only
`@Character1`, `@Character2`	Items from `reference_characters` only

Rejected Combinations

Input	Why rejected
Missing, empty, or more than one `reference_video_urls` item	An edit needs exactly one source video URL.
Edited window longer than 15 seconds	Edit window limit.
`end_frame` lower than `start_frame`	The frame range must move forward.
More than 5 `reference_image_urls`	Edit reference image limit.
More than 3 character items	Character item limit.
`image_url` on a character, or plain string character entries	Characters must be objects with `image_urls`.
`voice` and `custom_voice` on the same character	Use a preset voice or a tuned voice, not both.

Response

{
  "code": 200,
  "success": true,
  "data": {
    "task_id": "abc123def456",
    "status": "processing"
  }
}

Volume discounts are available for almost all models. Reach out at contact@unifically.com to discuss custom pricing.

​Model

​Parameters

​Billing

​Limits

​Character References

​Example — Edit Part of a Clip

​Prompt References

​Rejected Combinations

​Response

Model

Parameters

Billing

Limits

Character References

Example — Edit Part of a Clip

Prompt References

Rejected Combinations

Response