Talking photo
A talking photo is a still portrait animated to speak — lips synced to a script or recording, with natural head movement and expression. One photo becomes a short presenter video.
A talking photo chains several capabilities: a voice is synthesised or uploaded, the face is lip-synced to it, and subtle idle motion — blinks, small head tilts, breathing — keeps the clip alive between words. The result sits between a photo and a filmed take: not footage, but far more watchable than a static image with a voiceover.
A concrete example: a founder's headshot delivers the 20-second welcome message on a landing page — re-recorded by editing the script, not by booking a camera crew.
How Hermosso uses it: Talking Video makes a photo speak from a script or your own audio, and Photo to Video animates old family photos when you want motion without speech.
Try it on your own photos
Upload a few selfies, and Hermosso trains a private AI model of you — then generates studio-quality photos in any style. Your first credits are free.
Create your AI photos →