Today I was talking to some friends while playing ping pong and we were talking about voice cloning so we don't have to always respond to our moms calls for chores. Instead, we can clone our dad's voice and playback a recording that tells our mom to let the kids enjoy and do our thing. That got me thinking and I searched if anything like this was available or being working on Github to do as my first assignment on for Topic in Open Source Development course I am taking this semester. Luckily there is. I found a repository that uses deep learning framework that allows creating a numerical representation of a voice from a few seconds of audio. Which later is used in a condition for text-to-speech resulting in a cloned voice to say what you enter into a text box.
I was drawn to this the second I came by it but I was a bit against choosing this as my topic for my assignment since it was done in python. It makes sense to do it in python because of deep learning and useability but I have never used python before at all. So this could be a problem for me. In turn, I thought about killing two birds with one stone, learning python, semesters gonna be crazy busy now and work on something I like.