OpenWakeWord (the solution I also use in my Platypush setup) is actually very good at hotword detection, especially when paired with libspeex for noise suppression.

The STT models from Vosk are actually quite good too. The 180 MB English model is light enough to run on a RPi and it’s actually quite decent with clean accents. They also have a 1.8 GB model that is very accurate and that actually can still run fine on a RPi5 8 GB.

Yes, this is actually very similar to the setup I’ve had for years - just a RPi to do the STT+TTS part, and hooks in the background to control the right services.