Gemini Omni 1.2 Flash Video Edit: AI Video Editor

Edit videos with a text instruction using Gemini Omni 1.2 Flash. Restyle, replace, or adjust clips up to 15s with native audio. Try free. Gemini Omni 1.2 Flash — edit an existing video with a simple text instruction, optionally guided by reference images. Output length follows the source video (max 15s).

Interactive model controls

Gemini Omni 1.2 Flash — edit an existing video with a simple text instruction, optionally guided by reference images. Output length follows the source video (max 15s).

📝

Overview

About this model

Gemini Omni 1.2 Flash Video Edit transforms an existing video with a simple text instruction such as 'make this anime' or 'change the jacket to red', optionally guided by up to 5 reference images. Output length follows the source clip (up to 15 seconds), and the result keeps natively synchronized audio. Choose 360p to 4K output and 16:9, 9:16, or auto aspect ratio. Billing has two parts: the source video at $0.02 per second (rounded up) plus the output per billed second (min 3s): $0.028/s at 360p, $0.084/s at 720p, $0.126/s at 1080p, $0.252/s at 4K. To generate new video instead, see Gemini Omni 1.2 Flash, Gemini Omni 1.2 Flash Image to Video, Gemini Omni 1.2 Flash Reference to Video.

1Restyling: Convert live footage into anime, claymation, or illustrated looks.

2Object changes: Swap wardrobe, props, or backgrounds with a short instruction.

3Reference-guided edits: Add reference images to steer the subject or style.

4Social repurposing: Re-aspect and refresh existing clips for new channels.

5Rapid iteration: Preview edits at 360p before committing to 1080p or 4K.

💰

Pricing & Value

Cost analysis

Provider	Cost	Notes
muapi	$0.02/s source + $0.028–$0.252/s output (by resolution)	Pay-per-generation, no subscription. Source video billed per second (rounded up) plus output per billed second (3-15s).
Fal.ai	Not available	This model is not listed on Fal.ai.
Replicate	Not available	This model is not listed on Replicate.

muapi$0.02/s source + $0.028–$0.252/s output (by resolution)

Pay-per-generation, no subscription. Source video billed per second (rounded up) plus output per billed second (3-15s).

Fal.aiNot available

This model is not listed on Fal.ai.

ReplicateNot available

This model is not listed on Replicate.

** Competitor pricing is estimated based on similar model architectures and usage tiers.

⚙️

Technical Details

Configuration schema

Parameter	Type	Description	Default
Prompt	string	Describe the scene, action, camera movement, and sound.	`Make this video anime. Keep everything else the same.`
Source Video	string	URL of the video to edit (MP4 recommended, max 15 seconds).	`-`
Reference Images	array	Optional reference images (max 5) for subject, scene, or style guidance.	`-`
Aspect Ratio	Enum (3 options)	Output aspect ratio. `auto` follows the reference image and is treated as 16:9 when none is provided.	`16:9`
Resolution	Enum (4 options)	Output resolution. Output priced per second of generated video: $0.023/s at 360p, $0.07/s at 720p, $0.105/s at 1080p, $0.21/s at 4K.	`720p`

Promptstring

Describe the scene, action, camera movement, and sound.

Default ValueMake this video anime. Keep everything else the same.

Source Videostring

URL of the video to edit (MP4 recommended, max 15 seconds).

Default Value-

Reference Imagesarray

Optional reference images (max 5) for subject, scene, or style guidance.

Default Value-

Aspect RatioEnum (3 options)

Output aspect ratio. `auto` follows the reference image and is treated as 16:9 when none is provided.

Default Value16:9

ResolutionEnum (4 options)

Output resolution. Output priced per second of generated video: $0.023/s at 360p, $0.07/s at 720p, $0.105/s at 1080p, $0.21/s at 4K.

Default Value720p

📖

Implementation Guide

Developer documentation

How to Use Gemini Omni 1.2 Flash Video Edit

Provide the source video Pass a publicly accessible MP4 URL (max 15 seconds) as video_url.
Write a simple edit instruction Example: 'Make this video anime. Keep everything else the same.'
Optionally add reference images image_urls accepts up to 5 images for subject or style guidance.
Pick resolution and aspect ratio No duration is needed; the output follows the source. Billing: Source video $0.02/s plus output $0.028/s at 360p, $0.084/s at 720p, $0.126/s at 1080p, $0.252/s at 4K.
Submit and poll

curl -X POST https://api.muapi.ai/api/v1/gemini-omni-flash-1-2-video-edit
-H "Authorization: Bearer YOUR_API_KEY"
-H "Content-Type: application/json"
-d '{"prompt": "Make this video anime. Keep everything else the same.", "video_url": "https://example.com/clip.mp4", "resolution": "720p"}'

Then poll `GET /api/v1/predictions/{request_id}/result` until `status` is `completed`.

❓

Common Questions

Frequently asked

What is Gemini Omni 1.2 Flash Video Edit?

It edits an existing video from a text instruction and returns a new clip with synchronized audio.

How is it priced?

Source video $0.02/s plus output $0.028/s at 360p, $0.084/s at 720p, $0.126/s at 1080p, $0.252/s at 4K. Source duration is rounded up and output is billed for at least 3 seconds.

How long can the source video be?

Up to 15 seconds.

Do I set a duration?

No. Output duration follows the source video.

Can I use reference images?

Yes, up to 5 via `image_urls`.

What resolutions are available?

360p, 720p, 1080p, and 4K.