Sync 3 Avatar turns a still into a talking character, and works as well on drawings as on photos.
Sync 3 Avatar is the talking-head model from sync.so, the studio behind the lip-sync model Hiroska has carried for video since launch. Its distinguishing trait is tolerance for style: illustrations, painted characters and animation frames animate as convincingly as photographs.
The input list is as short as it gets: one image, one audio track, no prompt at all. That makes it the least fiddly way to get a mascot or an illustrated presenter speaking.
Same house as the video lip-sync model, so results cut together
What it costs
About 228 tokens ($2.28) per 10 s of audio; the exact price depends on the length of what you upload.
Settings
Tokens
Price
10 s of audio
228
$2.28
30 s of audio
658
$6.58
60 s of audio
1,299
$12.99
Prices come from the live catalog at $0.0100 per token, the pay-as-you-go rate; subscriptions include tokens at a lower rate. The exact price is shown before you generate, and a failed generation is refunded.
Questions
Does Sync 3 Avatar work on drawings and cartoons?
Yes, that is its strength. Illustrated characters and animation frames animate as readily as photographs, so a brand mascot can deliver a line.
Is there anything to configure on Sync 3 Avatar?
No. It takes an image and an audio track and nothing else, which makes it the quickest of the talking-head models to run.
Can I use Sync 3 Avatar on footage instead of a still?
For footage, use the video lip sync task. It comes from the same studio, but is built to re-voice a clip that already exists rather than animate a still.