ByteDance's audio-driven human video model, available via BytePlus. Upload one photo and one audio track — speech, song or dialogue — and get a video of that person performing it, with emotion and timing that follow the sound. Up to 5 minutes in a single continuous take.
0/300
Add a portrait and a voice track to continue.
Free preview · limited generations per hour · 720p · audio 4 s – 5 min
See how it works Powered by OmniHuman 2.0, available via BytePlus · Independent site
How it works
No rigging, no keyframes, no separate singing mode. Bring a face and a sound — the model does the performing.
A portrait, a selfie, or even a clay or drawn character. A plain background and a single clear face work best.
Speech, a song, or a dialogue — it's all the same input. There's no separate singing mode to switch on.
OmniHuman 2.0 renders a video of that person performing the audio — face, head and body — in one continuous take of up to 5 minutes.
TIP — a plain background and a single clear face give the best results.
Features
OmniHuman 2.0 hears tone, emotion and words — and turns all three into a believable on-camera performance.
5:00
The previous version capped out at 60 seconds. Now you get up to 5 minutes rendered continuously — no stitching.
The model listens for emotion and delivery. Laughs, whispers and pauses show up on the face, not just in the soundtrack.
Mouth shapes follow each syllable — including fast lines and long held notes in songs.
It generates face, head and body motion together, so the result reads as a performance rather than a pasted-on mouth.
Stitched clips — visible cuts
One take — continuous
Because nothing is stitched together, there are no sudden shifts in the face, the lighting or the background mid-video.
Works with photo portraits and selfies as well as clay figures, drawn characters and brand mascots.
Same input. No singing mode.
One model handles narration, singing and conversation. Just bring the audio — the model figures out the rest.
↓ cost
vs. previous version · per BytePlus
According to BytePlus, OmniHuman 2.0 is cheaper to run than the previous version — which means more minutes for your budget.
Spec sheet
Everything OmniHuman 2.0 needs, and everything it gives back.
Before / after
Typical lip-sync tools animate a mouth. OmniHuman 2.0 animates a person.
Use cases
From five-minute lessons to fifteen-second shorts.
Turn a script and an instructor photo into long-form lessons — up to 5 minutes per take.
02:48 / 05:00
Pricing · pay per use
No login, no credits, no subscription maze. Final prices haven't been announced — the options below are placeholders.
Pay once for one render. Good for trying it out.
$--/ video
Placeholder price
A bundle of renders for creators publishing every week.
$--/ pack
Placeholder price
For teams, agencies and course producers.
$--/ pack
Placeholder price
Prices, limits and features shown are placeholders and subject to change.
FAQ
Can't find what you need? Everything about inputs, length and availability is here.
OmniHuman 2.0 is ByteDance's audio-driven human video model, released via BytePlus on October 15, 2026. You give it one photo and one audio track, and it generates a video of that person performing the audio.
Just two things: a single photo and a single audio track. The audio can be speech, a song or a dialogue.
No. Singing uses exactly the same input as speech — upload the song and the model handles it, including fast lyrics and long held notes.
Up to 5 minutes in one continuous take. The previous version was capped at 60 seconds. Because the video isn't stitched from shorter pieces, the face, lighting and background stay consistent throughout.
No. Plain lip sync only moves the mouth. OmniHuman 2.0 generates the face, head and body performance, and it reacts to tone and emotion — so laughs, whispers and pauses show on the face.
Yes. Besides real portraits and selfies, it works with clay and drawn characters and mascots.
Use a photo with a plain background and a single, clearly visible face. Clean audio without heavy background noise also helps.
No. There is no login and no credits system. Pricing will be simple pay-per-use; checkout details are coming soon.
No. OmniHuman2.net is an independent service and is not affiliated with, endorsed by, or sponsored by ByteDance or BytePlus. All trademarks belong to their respective owners.
One photo · one track · up to 5:00
One photo, one track, up to five minutes of continuous performance.
Photo + audio → video
Up to 5 min in one take
