AI Box

Generation language

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

custom avatars

Cast your digital twin in five minutes.

Generate a custom avatar from a single portrait — yours, an actor's, or a description-only spec — then pair it with a voice clone to render 'you' on demand. Save Personal Clones so every future render uses the same face, framing, and voice.

cost

Model-weighted (3-6 credits)

powered by

FLUX Kontext Max · Seedream 4 +3

live preview
● rec

why it matters

Built for the way creators actually work.

benefit 01

Photo-in, avatar-out

Upload a single portrait and we extract identity, framing, and lighting. The avatar stays recognizable across hundreds of future renders without ever drifting.

benefit 02

Or design from scratch

No photo? Describe the look — 'Hispanic woman, 30s, soft studio light, neutral knitwear' — and FLUX Kontext Max generates an avatar that holds together across renders.

benefit 03

Personal Clones bundle face + voice

Save the avatar with its linked voice clone. One click renders 'you' with the right face and the right voice every time — no more re-uploading on every render.

benefit 04

Drop into any UGC pipeline

Avatars flow into UGC Video, Avatar UGC, Multi-Scene UGC, and the Product Ad Wizard. Same identity, different scripts and scenes.

how it works

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

Upload or describe

Drop a portrait photo (yours, actor's, stock) or write a description. The face you generate is the face you render with going forward.

Pick the framing

Headshot, half-body, or full-body. Aspect ratio aware — 9:16 for TikTok / Reels, 16:9 for YouTube, square for Instagram feed.

Link a voice

Attach an existing voice clone or train a new one from a 30-60s sample. The bundle becomes a Personal Clone you can render with in one click.

Save + reuse

Personal Clones live in My Brand → Avatars. Activate one and every render inherits the face, framing, and voice automatically.

built for

Made for the people shipping shorts.

Faceless creators going on-camera

Build a brand-safe digital twin without ever turning on a real camera. Same face, same voice, every video.

Multi-language localizers

One avatar, multiple voice clones in different languages. Run the same script as five regional voiceovers without re-rendering the visual identity.

Agencies onboarding clients

Cast a custom avatar per client. Each client's Project locks their avatar + voice as the default — no mix-ups.

Course creators

Render dozens of consistent on-camera lessons in an afternoon. Pair with Narration Prompt for full pipeline scale.

models in the loop

FLUX Kontext MaxSeedream 4Nano BananaRecraft V3OmniHuman

briefing notes

Questions worth answering.

play in the same band

Pairs well with.

no card · cancel anytime

Build an avatar in 60 seconds.

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

See pricing