There's an important detail here -- an advantage of mRNA vaccines is that mRNA does not last all that long in cells [1]. Thus, even if the cells live a long time, they won't produce spike proteins for very long (instructions for the production will be degraded and thus not available).
The vaccine's longer-term effectiveness comes from the immune system's memory B cells response to the short-lived expression of spike proteins.
Built it and took a fullscreen screenshot with GIMP to figure out the width/height/x/y coordinates I wanted and tested with Google Meet. Working perfectly!
I commend the authors on making this easy to try! However it doesn't work very well for me for general voice cloning. I read the first paragraph of the wikipedia page on books and had it generate the next sentence. It's obviously computer generated to my ear.
All I did was install the packages with pip and then run "demo_part1.ipynb" with my audio sample plugged in. Ran almost instantly on my laptop 3070 Ti / 8GB. (Also, I admit to not reading the paper, I just ran the code)
You have a custom prompt enabled (probably from viewing another one and pressing "start over") that is asking for opposites which will increase the noise a lot.
The entire thing is frontend only (except for the share feature) so the server never sees your key. You can validate that by watching the network tab in developer console. You can also make a new / revoke an API key to be extra sure.