Talking photo (InfiniteTalk)
A portrait that speaks or sings your audio with lip sync and natural head movement - audio up to 10 minutes, at 480p or 720p.
Avatar Studio turns one portrait and an audio clip into a talking or singing video, or swaps the head in a video for the one in a reference portrait. Your price is worked out from the real length of your audio or video before you generate.
Style previews are licensed stock footage, not output of these tools.
A portrait that speaks or sings your audio with lip sync and natural head movement - audio up to 10 minutes, at 480p or 720p.
A lifelike avatar video from one photo and one audio clip, up to 64 seconds.
Replace the head in a video (up to 120 seconds) with the one in a reference portrait.
Use a presenter photo, a pet portrait or an illustrated character as the starting image.
Availability and options can change; the app always shows what each model supports right now.
FARZI Studio is pay as you go in US dollars: you add balance to your wallet and each generation is charged from it - there is no subscription to buy.
Before anything is generated the app shows the exact price for your settings. That is the amount taken from your balance, and if a generation fails it is returned in full.
From the real length of your audio or video, measured by FARZI Studio, rounded up to whole seconds with a 3-second minimum. You see it before generating.
Only your own, or with the permission of every person shown or heard. FARZI Studio asks you to confirm this for every avatar video and does not create sexual, deceptive or impersonating content.
Photos as PNG, JPG or WebP; audio as MP3, WAV or M4A; video as MP4 or MOV.
It is shown in Avatar Studio with download, gallery and editor options, and listed in your usage history.
Open FARZI Studio in your browser - nothing to install.