A model that fits lips to a new audio track and holds the face more carefully. You pay for every second of the clip, so it suits short fragments and key close-ups where quality matters more than price.
| What it does | Fits lips to new audio |
|---|---|
| Input | A clip and a ready track |
| Price per second | about $0.091 |
| A 5-second clip | $0.46 |
| A 30-second clip | $2.73 |
| Strong side | Holds the face carefully |
In the service catalog this is its main note: the features stay in place and only the lips change. For a close-up this matters more than price.
About $0.091 per second of clip: 5 seconds cost $0.46, 10 seconds $0.91, 30 seconds $2.73.
If the clip has one key shot with a face, fit only that one. That way you pay for the seconds you really need.
A 60-second clip costs $5.46. For long recordings LatentSync is better: its price is fixed up to 40 seconds and grows slowly after that.
It holds the face more carefully, while LatentSync is cheaper on clips up to 40 seconds. If in doubt, test both on a short fragment.
$0.91. The same clip in LatentSync costs $0.26.
Make a voiceover in the “Voice only” mode, for example with ElevenLabs Turbo, or upload your own track: a voice-recorder file will do.
The service counts the price by the clip you upload, so upload only the fragment you need and pay for its seconds.