This has been my dream for voice control of PC for ages now. No wake word, no button press, no beeping or nagging, just fluently describe what you want to happen and it does.

Apple tried this ages ago:

https://en.wikipedia.org/wiki/PlainTalk

without a wake word, it would have to listen and process all parsed audio. you really want everything captured near the device/mic to be sent to external servers?

I might if that's what it takes to make it finally work. The fueling of the previous 15 years was not worth it, but that was then.