Deep Score is a Tokyo-based company that claims to use facial recognition and voice recognition to essentially classify you or detect whether you are trustworthy. Their accuracy I think is very low at 70%. There's just nothing respectable on that. If it did, we would be using it in police work and so on. And the technology does exist. That really does it properly. But here with just voice and audio, you're going to get a lot of false positives and a lots of false negatives as opposed to maybe more reliable techniques. It doesn't seem like a good idea as far as I can tell.