I was experimenting with voice cloning and tried to replicate my own voice using a small, poorly recorded dataset. The result was not what I expected.
I ended up with a voice that sounds like someone was dragged from hell and put into a recording booth. The entire thing was vibe coded together in a few hours.
I ended up with a voice that sounds like someone was dragged from hell and put into a recording booth. The entire thing was vibe coded together in a few hours.
Would love to hear your thoughts!