# OmniHuman 1.5

Give it one photo of a person and a recording, and it makes them say it. Built for talking.

Model id: `omnihuman-1.5`
Type: Video
Made by: ByteDance
Inputs: Text, First frame, Audio
Length: 1 to 30 s
Resolution: 720p, 1080p
Updated: Oct 12, 2026

Coming soon.

## Pricing

| Setting | MiniAPI | fal | Difference |
| --- | ---: | ---: | ---: |
| any | $0.16 / s | $0.16 | +0% |

You are not charged for a job that fails.

## Parameters

| Name | Required | Values | Default | Description |
| --- | --- | --- | --- | --- |
| `prompt` | No | text |  | What to make, in plain words. |
| `image_url` | Yes | https URL |  | A picture to start from. We fetch it and keep a copy for the job. |
| `audio_url` | Yes | https URL |  | The sound to use. |
| `mask_url` | No | https URL |  | A black and white picture: white is the part to change. |
| `turbo_mode` | No | true, false | false | Generate a video at a faster rate with a slight quality trade-off. |
| `resolution` | No | 720p, 1080p | 1080p | Output size. Higher is sharper, slower and costs more. |

Page: https://api.minicut.ai/models/omnihuman-1.5
API reference: https://api.minicut.ai/docs/api