A: Hi! We have two lip-sync deepfake models available on Yapper: Sync-Max and Sync-Pro.

Sync-Max is the highest quality studio-grade sync model we offer but it's only available to some example videos. If you'd like to use it on a video that you upload or an example where Sync-Max is not yet available, you'll have to wait ~30-40 minutes for a custom model to train on your first generation. However, all subsequent generations will take just the usual 2-5 minutes.

Sync-Pro is also an extremely accurate model, but it can have some visual artifacts. It's often cheaper and faster than Sync-Max while still producing high quality output. Sync-Pro is perfect for most recreational use cases.