OmniHuman 2.0
One photo of a person and one audio file become a video of them talking or singing, in sync.
Prompt: She talks warmly to the camera like on a video call, small natural head nods and a light laugh at the end, gentle hand gesture, steady framing.
- 3:4
- 12s
- 720p
OmniHuman 2.0
Your portrait, your audio, one lip-synced take.
Use a recorded voice, a text-to-speech line or a song. An optional prompt of up to 300 characters steers the setting, the person's gestures and the camera.
Best for
- Presenter and explainer clips from a single headshot
- Singing portraits for music and social posts
- Voiceovers that need a face on screen
Pick another model for
- Scenes without a person in front of the camera
- Choosing the length, resolution or aspect ratio yourself
Specs
- Inputs
- 1 portrait + 1 audio, optional prompt
- Audio
- MP3 or WAV, 4 to 300 s, up to 15 MB
- Portrait
- 300 to 6000 px per side, up to 30 MB
- Length
- Same as the audio
- Resolution
- 720p
- Prompt
- Optional, up to 300 characters
See pricesHide prices
Price
| Option | Rate | Unit |
|---|---|---|
| OmniHuman 2.0 | 19 | credits / sec |
How the family fits together
OmniHuman is a talking-portrait model. You give it a face and a voice, it gives you that person delivering the audio, with lips, face and head moving to the sound. There is nothing to set: the video is 720p and exactly as long as your audio.
Getting a clean take
- Use a sharp, front-facing photo with the mouth visible and nothing covering the face.
- Trim silence from the start and end of the audio: you pay for every second of it.
- Keep the prompt about mood and movement, the audio already decides the words.
Pick a plan
One credit balance covers images, video and audio. Pick the size that fits how much you make.
Studio Pro
Studio value with extra headroom.
2 seats included
What you'll generate
- Images~1,600
- Songs~457
- Videos~640
- Separations~1,066
- Caption Minutes~213
- All modelsIncluded
Starter
Low tier generations for regular use.
What you'll generate
- Images~275
- Songs~78
- Videos~110
- Separations~183
- Caption Minutes~36
- All modelsIncluded
Pro
Access full experience.
What you'll generate
- Images~650
- Songs~185
- Videos~260
- Separations~433
- Caption Minutes~86
- All modelsIncluded
Powerhouse
Most cost efficient.
13,000 credits/mo
Extra seats €19/seat/mo
What you'll generate
- Images~3,250
- Songs~928
- Videos~1,300
- Separations~2,166
- Caption Minutes~433
- All modelsIncluded
Enterprise
For teams that outgrow standard plans.
Pricing tailored to your team
What's included
- Custom number of seats
- Custom credit volume
- Invoice billing
- Priority support
Starter
Low tier generations for regular use.
What you'll generate
- Images~275
- Songs~78
- Videos~110
- Separations~183
- Caption Minutes~36
- All modelsIncluded
Pro
Access full experience.
What you'll generate
- Images~650
- Songs~185
- Videos~260
- Separations~433
- Caption Minutes~86
- All modelsIncluded
Studio Pro
Studio value with extra headroom.
2 seats included
What you'll generate
- Images~1,600
- Songs~457
- Videos~640
- Separations~1,066
- Caption Minutes~213
- All modelsIncluded
Powerhouse
Most cost efficient.
13,000 credits/mo
Extra seats €19/seat/mo
What you'll generate
- Images~3,250
- Songs~928
- Videos~1,300
- Separations~2,166
- Caption Minutes~433
- All modelsIncluded
Enterprise
For teams that outgrow standard plans.
Pricing tailored to your team
What's included
- Custom number of seats
- Custom credit volume
- Invoice billing
- Priority support
Test any model with one-time credit packs
Credits never expire and don't require a subscription — buy a pack, generate, see if Kubeez fits.
Quick refill
Quick refill for short bursts of generation.
Credits
500
You pay
€6
Standard pack
Mid-size pack at the standard per-credit rate.
Credits
1,500
You pay
€18
Volume pack
Larger pack with a volume discount built in.
Credits
5,000
You pay
€60€57
Production pack
Best per-credit price for sustained production.
Credits
15,000
You pay
€180€162
Frequently asked questions
Exactly as long as your audio, from 4 seconds to 5 minutes. Kubeez measures the file itself and bills those seconds.
MP3 or WAV under 15 MB. Speech, voiceover and songs all work. Make a voice line first with a Kubeez text-to-speech model if you need one.
It is built for a person's face. Clear, realistic portraits give the most reliable lip sync.
No. Output is 720p and follows the shape of your portrait, so crop the photo the way you want the video framed.
Yes. The model id is omnihuman-2-0. Upload the audio through Kubeez first so its length can be measured, then send the portrait and the audio together.
Guides and comparisons
Tests, comparisons and how-tos for OmniHuman from the Kubeez blog.
- Make a Photo Talk or Sing With OmniHuman 2.0Make a photo talk or sing on Kubeez: voice a line with text to speech, pick a portrait that syncs well and turn both into a lip-synced OmniHuman 2.0 video.
- OmniHuman 2.0 on Kubeez: Make a Photo Talk or SingOmniHuman 2.0 is live on Kubeez: one portrait and one audio file become a lip-synced 720p video of that person talking or singing, as long as the audio.
Open OmniHuman in the studio
Pick the model that fits your job, write your prompt and run it.