Researchers in the UK claim to have translated the sound of laptop keystrokes into their corresponding letters with 95 percent accuracy in some cases.
That 95 percent figure was achieved with nothing but a nearby iPhone. Remote methods are just as dangerous: over Zoom, the accuracy of recorded keystrokes only dropped to 93 percent, while Skype calls were still 91.7 percent accurate.
In other words, this is a side channel attack with considerable accuracy, minimal technical requirements, and a ubiquitous data exfiltration point: Microphones, which are everywhere from our laptops, to our wrists, to the very rooms we work in.
Another advantage to the split keyboard
This attack is useless in the real world.
That said, what gives you the idea a split keyboard (if they had a sample of you typing on it etc) would be any different than a normal one?
It is just another keyboard with a different sound profile.
You can remap and customise keys to be whatever you want. There's even auto shift, so if I hold certain key just a bit longer than a regular tap, it will automatically capitalise or whatever the shift + key combo would result in. There are also multiple layers you can easily activate with a press of a button, so the layout is something totally different.
Example: https://configure.zsa.io/moonlander/layouts/default/latest/0/
Layer 0
Layer 1
Layer 2
It was just a joke