While everything works quiet smooth with Jogg AI, my first Custom Avatar video can be way better if 2 things are provided.

Render Export Quality - 1080 Pixels or Higher would be very helpful. Lower output quality causes issues with lip sync area.

Audio Speed - Since for short form videos, speed of audio is of the essence. It would be great if we can speed up to audio to 1.1x or 1.2x, it produces better outputs that way.

I am attaching 2 outputs here, one is from Heygen and one is from Jogg AI. Here is a Head to Head Comparison in terms of Lip Sync, Render Quality and Audio Speed.

Jogg AI - https://share.zight.com/5zuoq795
HeyGen - https://share.zight.com/mXuQXjPq

The Potential for Jogg AI is huge, with minor improvements they can be on their way for a good market share.