OmniHuman 1.5

Coming soon

Give it one photo of a person and a recording, and it makes them say it. Built for talking. Made by ByteDance. 1 to 30 seconds, 720p, 1080p. From $0.16 a second.

omnihuman-1.5

Get API key API reference Add funds

TypeVideo

InputsText, First frame, Audio

Length1 to 30 s

Resolution720p, 1080p

SoundNo

From$0.16 / s

UpdatedOct 12, 2026

Pricing

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

Example costs

Setting	1 s	16 s	30 s
any	$0.16	$2.56	$4.80

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.

Compare

Model	Maker	Max length	Resolution	Sound	From	vs fal
OmniHuman 1.5	ByteDance	30 s	720p, 1080p	No	$0.16 / s
Seedance 2.5	ByteDance	30 s	480p, 720p, 1080p	Yes	$0.16 / s	-27%
Seedance 2.0	ByteDance	15 s	480p, 720p, 1080p, 4K	Yes	$0.10 / s	-26%
Kling 3.0	Kling	15 s		Yes	$0.0924 / s
Google Veo 3.1	Google	8 s	720p, 1080p, 4K	Yes	$0.11 / s