I don't know if this topic has already been discussed, maybe in the future music recognition can be added

https://audd.io/

 This is not free

PRICING
0+ requests per month - $5 per 1000 requests ($2 for the first 1000);

Maybe we can say:

  • what are we listening to?
  • what is this music?
  • I love this song

InMoov starts listening.

Or after a while without talking to him, maybe he can go into music detection mode every x time and when he detects the song, he can say a phrase with the name of the song or showing the lyrics, etc.

Or if he detects a song that we already have programmed in a script, he could sing or dance, but that is too much hahaha.

But I think that all this can also interfere with speech recognition.