There's a subtle modulation that happens on all of the samples. It sounds almost like some kind of harmonic or phase shift? This is something I notice with every AI generated speech out there.
Add onto that the fact the 8th and 10th gen Intel low power mobile parts are, well, kinda garbage (low perf/watt, very little boost time, low core count) and were quickly obsoleted.
I'm not sure why Msft put that CPU and RAM combo in their own device when it's just barely past the minimum specs for Windows 10 let alone 11.