AI Box

Generation language

Default language for AI-written scripts, TTS voiceovers, and captions. You can still override per-job.

talking head

Your face, your script, no camera.

Upload a single portrait — yours, an actor's, or a generated one — and we render a lip-synced talking-head video in your aspect ratio of choice. Bring a voice clone for true creator continuity, or pick from the TTS catalog.

cost

Model-weighted (5-12 credits)

powered by

OmniHuman · Hedra Character-3 +2

live preview
● rec

why it matters

Built for the way creators actually work.

benefit 01

OmniHuman + Hedra full-body

OmniHuman gives you natural body motion (gestures, weight shifts, head turns) instead of the floating-head look. Hedra Character-3 nails facial micro-expressions.

benefit 02

Voice clone friendly

Pair an OmniHuman render with your voice clone and the talking head matches your real cadence — perfect for faceless / faceless-with-twin creator setups.

benefit 03

Bring your own

Upload any portrait — a photo of yourself, a generated avatar, a stock photo. Personal Clones save the photo + voice link so you can render 'you' with one click.

benefit 04

Studio quality controls

Pick aspect ratio, framing (close / medium / full body), caption style, and brand colors. Hand off to Multi-Scene UGC for narrative continuity.

how it works

4 steps.
Most of it is the model, not you.

Pick or upload an avatar

Use a Personal Clone you've saved, pick from the avatar library, or upload a fresh portrait.

Write the script

Or generate it from the Prompt Studio. Add a hook style if you want Opus to sharpen the opener.

Pick voice + model

TTS voice or your own clone. OmniHuman for full body + natural motion, Hedra for facial nuance, Wan S2V for cheap iteration.

Render + caption

Lip-sync runs at native frame rate. Burned captions, brand colors, optional music bed. Schedule the post or download the file.

built for

Made for the people shipping shorts.

Faceless creators with a digital twin

Render 'you' on demand without ever turning on a camera. Same face, same voice, every video.

Educators + course makers

Make consistent on-camera explainer clips at scale. Pre-record your voice clone, render dozens of short lessons in an afternoon.

Affiliate / DTC brands

Cast a generated 'creator' once, render testimonial-style spots across SKUs without re-shooting.

Localized markets

Same avatar, different voices and translated scripts. One creator face, every language.

models in the loop

OmniHumanHedra Character-3SonicWan S2V

briefing notes

Questions worth answering.

play in the same band

Pairs well with.

no card · cancel anytime

Try Avatar UGC in 60 seconds.

Free plan includes 50 credits and the workspace, projects, brand kit, and saved prompts. Upgrade when you outgrow it.

See pricing