Model · Talking presenters, Video

OmniHuman

A ByteDance model that turns one photo plus a voice or music track into a video of that person talking, singing or moving, from head-and-shoulders up to full body. Not downloadable; businesses pay per second through ByteDance's BytePlus cloud.

Go to OmniHuman’s website

At a glance

Open or closed: Closed
Only usable through the maker's app or API
Research page says the team offers no downloads; no weights or code released.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence: BytePlus service terms (The maker's own terms)
Terms for the BytePlus API were not read.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Can I sell what I make?: The terms don't say clearly
Product page sells API access to businesses but doesn't state output rights; BytePlus terms not read.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Cost: No free plan.
Plans below.
How you use it: Maker's own API
Official API through BytePlus; native 1080p output. ByteDance's consumer apps may also use it but this was not checked.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Skill needed: Technical
Our judgement: API only from the maker.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: ByteDance
Research page credits ByteDance Intelligent Creation; offered commercially by BytePlus. No company address read, so no country.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
BytePlus page centres on version 1.5; 1.0 still appears but without details.
source · checked 12 Oct 2026 · checked on the maker's own page

What you can make with it

A talking presenter, a talking version of a photo (main use)
A video, by bringing a photo to life
A video, by copying movement from another video

audio to videoimage to videovideo to video

Driven mainly by audio (speech or singing); can also copy movement from a reference video. Works on cartoons and animals too.

source · checked 12 Oct 2026 · checked on the maker's own page

Plans and prices

Plan	Price	Includes
OmniHuman 1.5 API	$0.12 per seconds of video

Some plans are not listed here; see the source for the full list.

Two different per-second prices on the same page; confirm before budgeting.

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Rights and safety

Real faces and voices: Copies a real face (animate any photo via API), no consent step
Works from any single photo. API docs list an optional 'subject recognition' step but don't say what it checks; no consent step described.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review

Other options for “A talking presenter, a talking version of a photo”

Akool, D-ID, DeeVid AI, DomoAI, Dreamina, Dzine, EchoMimic, Elai.io, fal, FantasyTalking, Hallo2, Hedra, HeyGen, HunyuanVideo-Avatar, InfiniteTalk, Jogg AI, LivePortrait, Magic Hour, MuseTalk, SadTalker, VEED, Vidnoz AI, Vozo, WaveSpeedAI

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.