strange osprey
Try it with instant voicecloning first. Some voices are perfectly working with the instant voice clone.
just imagine:
They read the voice you put in, and try to find a voice they already did training with and tweak that a little to make it sound like the one you put in. If there is a "Base Voice" that sounds close to yours, instant voice cloning should work fine.
if there isnt, it will be very hard to hit the sweet spot with the instant voice clone.
Then I recommend to put in the professional voice clone. That takes a while but I had great results with only 60min of high quality input, though they recommend up to 3h to make it perfect