Biggest thing is you need a nice mic that's very close to your face, like you might see on a twitch stream. Good noise isolation via a directional mic off-camera is quite difficult/expensive apparently.
Instead, sound engineers spend weeks cleaning up spoken dialog by hand in spectrogram editors. It's honestly astounding the magic they can do, but it's also labor-intensive and therefore expensive. They're literally individually EQ-ing every vowel, splicing consonants from one word to another... it's wild.