How do you guys create voices with Genny for short videos (TikTok/Reels) to sound as natural as possible?

I'm using Genny Lovo AI to create voices for short videos (TikTok and Reels), and I'm really impressed with the quality of Genny's voice—especially the English and Korean voices, which sound extremely natural. However, when combined with background music and effects, the voice sometimes still sounds a bit "AI" and lacks emotion.

I'd like to ask for more experience from everyone:

How do people usually adjust the tone, speed, or pause to make the voice sound more real?

Has anyone tried using scripts with expressions or exclamation points (like "wow," "uhm," "really?"...) to increase the naturalness?

Also, do you have any tips for that's not my neighbor syncing voice and video to match emotions?

I'd love to learn more from you guys. 💡