AI avatar video generator from one photo

    Upload a portrait and a voice track. Get back a talking video with the lips in sync.

    Start creating

    Presenters and course videos

    One headshot and one voice line make a presenter who looks into the lens and says your script. Use it for sales videos, course lessons and product explainers, with no studio, camera or crew to book.

    Start creating
    OmniHuman 2.0

    Sales pitch

    Prompt

    He pitches his coffee to the camera with quiet pride, small nods, a brief smile, one hand resting on the counter, natural blinks, steady framing.

    Try this prompt

    A coffee roaster pitches his monthly bags straight to camera, made with OmniHuman 2.0 from one portrait.

    P-Video

    Course lesson

    Prompt

    She teaches an online pottery lesson to camera, lips in sync with her voice, wet hands resting on the clay on the wheel, calm nods and small gestures, natural blinks, steady locked off framing.

    Try this prompt

    A ceramics teacher opens a pottery lesson at her wheel, her lips following a calm voiceover.

    P-Video

    Product explainer

    Prompt

    He explains the product to camera in a sunny living room, lips in sync with his voice, relaxed hand gestures toward the plants beside him, small natural head movements and blinks, steady locked off framing.

    Try this prompt

    A presenter explains a plant watering app and points at the pots beside him as he talks.

    Reviews, promos and news reads

    Talking avatars fit the formats people already watch: a phone style review, a shop promo in Spanish, a news desk read. The video takes the shape of your photo, so a vertical portrait gives you a vertical clip.

    Start creating
    P-Video

    Vertical testimonial

    Prompt

    Handheld front camera selfie video: she talks to the lens in her kitchen, lips in sync with her voice, amused honest expressions, slight natural sway of the arm holding the camera, her other hand stays out of frame, no phone or object in her hands, unpolished creator footage.

    Try this prompt

    A selfie style blender review in 9:16, kitchen light and shaky hand included, ready for reels and stories.

    OmniHuman 2.0

    Spanish shop promo

    Prompt

    She greets customers warmly from behind the counter, bright smile, small head tilts, a little wave of her hand toward the bread, natural blinks, steady framing.

    Try this prompt

    A baker announces fresh conchas in Mexican Spanish, from one portrait and a Spanish voice line.

    P-Video

    News anchor read

    Prompt

    The anchor reads the evening weather story straight to camera, lips in sync with her voice, composed small head movements, hands folded on the desk, natural blinks, the skyline behind her stays still, locked off broadcast framing.

    Try this prompt

    An evening weather report read at the anchor desk, hands folded and eyes on the camera.

    Characters, paintings and songs

    The face does not have to be a photo. P-Video gives a clay character or an oil painting a voice, and OmniHuman 2.0 makes a portrait sing, with the lips and head moving to the music.

    Start creating
    OmniHuman 2.0

    Singing portrait

    Prompt

    He sings with feeling on a small stage, eyes half closed on the long notes, warm spotlight.

    Try this prompt

    A soul singer holds the notes of an original ballad, lip synced to a verse made with a Kubeez music model.

    P-Video

    Talking clay character

    Prompt

    A friendly clay animated owl librarian in a tiny wooden library speaks directly to camera, beak moving in sync with the voice, blinking, with small head tilts and wing gestures, stop motion feel.

    Try this prompt

    A clay owl librarian warns cracker eaters away from the poetry shelf, beak and wings moving with the voice.

    P-Video

    Talking painting

    Prompt

    The woman in the oil painting comes alive and speaks to the viewer, lips in sync with the voice, a raised eyebrow, a slow flick of the fan, subtle head turns, the brushwork and canvas texture stay intact, static framing.

    Try this prompt

    An 18th century style portrait complains about three hundred years on a museum wall.

    Why make avatar videos on Kubeez

    • The voice track sets the language

      The lips follow the sound, not a script, so the avatar speaks whatever your audio speaks. This grandfather shares his polenta secret in Romanian. Make the line with the Kubeez voice generator or upload your own recording.

    • Longer takes from one photo

      P-Video lip syncs clips of up to 20 seconds, like this 19 second trail briefing. OmniHuman 2.0 follows a voice track from 4 seconds up to 5 minutes, in 720p.

    How it works

    1. 1

      Add a portrait

      A photo, a drawing or a character. One face, looking toward the camera.

    2. 2

      Add the voice

      Upload a recording, or write the line and make the voice in Kubeez first.

    3. 3

      Generate and download

      The lips follow the audio. Download the clip to post or use anywhere.

    Pick a plan

    One credit balance covers images, video and audio. Pick the size that fits how much you make.

    Most popular

    Studio Pro

    Studio value with extra headroom.

    49 €month
    6,400credits / month
    Team seats

    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.

    10 €month
    1,100credits / month

    What you'll generate

    • Images~275
    • Songs~78
    • Videos~110
    • Separations~183
    • Caption Minutes~36
    • All modelsIncluded

    Pro

    Access full experience.

    20 €month
    2,600credits / month

    What you'll generate

    • Images~650
    • Songs~185
    • Videos~260
    • Separations~433
    • Caption Minutes~86
    • All modelsIncluded

    Powerhouse

    Most cost efficient.

    99 €month
    13,000credits / month

    13,000 credits/mo

    Team seats
    3 seats

    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.

    Custom

    Pricing tailored to your team

    What's included

    • Custom number of seats
    • Custom credit volume
    • Invoice billing
    • Priority support
    Or pay-as-you-go

    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

    −5%

    Volume pack

    Larger pack with a volume discount built in.

    Credits

    5,000

    You pay

    €60€57

    −10%

    Production pack

    Best per-credit price for sustained production.

    Credits

    15,000

    You pay

    €180€162

    Questions

    • Signing up is free and new accounts get starter credits to try it. After that you buy credits or pick a plan. There is no permanent free tier.

    • As long as the audio. OmniHuman 2.0 takes a voice track of 4 seconds to 5 minutes, and P-Video lip syncs clips of up to 20 seconds.

    • No. Write the line and generate it with the Kubeez voice generator, or upload your own MP3 or WAV. The avatar says exactly what the audio says.

    • Yes. P-Video lip syncs stylized faces, like the clay owl and the oil portrait above. OmniHuman 2.0 is built for realistic faces and gives the cleanest sync on photos.

    • The lips follow the audio, not a script, so your voice track sets the language. The clips on this page speak English, Spanish and Romanian.

    Make your first one now

    Sign up, open the dashboard and start from a portrait and a voice line.