Skip to content
Avatar & lip-sync model · ByteDance

OmniHuman 1.5

One photo + audio → a realistic talking, gesturing presenter.

100 free credits · no credit card

At a glance

Category
Avatar & lip-sync
Made by
ByteDance
Price on Vidova
≈320 credits / 10 s
Output
Video
Accepts
Text prompt, Image, Audio
Resolutions
720p · 1080p
Native audio
No

Prices are for default settings. You always see the exact cost before you generate, and failed generations are refunded automatically.

Made with OmniHuman 1.5 on Vidova

No public creations yet — make one and be the first on Explore.

Frequently asked questions

How much does OmniHuman 1.5 cost on Vidova?

≈320 credits / 10 s at default settings. Credits come with every plan or as never-expiring credit packs, and a failed generation is refunded automatically.

Can I try OmniHuman 1.5 for free?

Yes. Every new Vidova account gets 100 free credits that work with OmniHuman 1.5 and every other model — no credit card required.

What can I give OmniHuman 1.5 as input?

OmniHuman 1.5 accepts: Text prompt, Image, Audio. It returns Video.

Can I use OmniHuman 1.5 results commercially?

Yes, on any paid plan you can use what you create commercially, without a watermark. The Free plan is for personal use.

Every top AI model. One account.

Start with free credits, pay only for what you generate, and get refunds for failed runs automatically.

100 free credits · No credit card