An AI clone of yourself from one photo

A digital twin on Percify takes one photo and 15 to 30 seconds of your voice. Your own photo is the face, so there is nothing to pay for it; new styled pictures of you are 5 credits each. Saving your cloned voice is free. After that, a talking video is 2 credits a second (about $2 to $3.20 a minute) and speech is 2 credits for up to 40 words. No watermark, and you own what you make.

You upload one clear photo. There is no scanning session, no turntable and no video capture. Because a lip sync model rebuilds the mouth region rather than animating a rig, the photo decides quality more than any setting does. The rules are unglamorous:

• The face fills at least a third of the frame. Below about a quarter of the frame width there is not enough mouth detail to rebuild.
• Nothing across the mouth: no hand, no microphone, no stray hair.
• Even, frontal light. Hard side light bakes a shadow into every frame generated from it.
• A neutral or slightly open mouth. A wide smile is a hard starting position to animate out of.

The voice clone needs at least 5.6 seconds of you talking. Anything shorter is padded by repeating the clip to about 6.2 seconds so the request still works, but a three second clip looped twice still holds three seconds of vocal information, and the clone comes out flat.

Record 15 to 30 seconds and say something with range in it: a question, a statement, a number. Room matters more than microphone. Curtains, a sofa or a bed beat bare walls and an expensive mic. Keep a steady distance, and normalise the levels if they swing.

Once a face and a voice exist, they are inputs everywhere. Platforms that build the presenter for you keep the likeness inside their product; a twin you own can be pointed at any of these. See the talking head generator, the AI podcast generator and remaking a viral video.

Most people spend their first credits on a stock presenter, decide the result is fine but impersonal, and only then wonder whether they could have used themselves. Cloning first costs nothing extra and makes everything afterwards yours. A talking video of your clone is 2 credits a second.

Your own face and voice are the easy case. A colleague, a client or a public figure is not, whatever a tool will technically accept. Rules such as the EU AI Act are converging on disclosure for synthetic likenesses, and provenance standards like C2PA attach a signed record of how a file was made.

Decide your disclosure position once, deliberately, rather than after someone asks. The checklist is in ethical AI video generation.