Haha this is so epic, well done everyone!
I love the interface and overall experience using it and it's just such a brilliant way to raise awareness of the Mercury Phoenix Trust and their battle against HIV/AIDS 😍
It's also awesome that "your audio doesn’t get uploaded to servers to be analyzed, so your vocals stay private".
I'd love to hear some more detail on how you approached the "AI" part - are you using an RNN to encode small clips and comparing them using cosine-similarity to an encoding of Freddie's version or something else?