Robot voice control on ESP32 with INMP441 microphone and TTS pcm5102

Hello

Has anyone done something like this?
I'm reviewing the topic because I would like to do a simple voice control of a talking robot for demonstration purposes.
I have a pcm5102 to TTS and it works great but now I need to the other way.

There are some projects based on AI which require some api keys, which according to what I have read is not free.

But what you can get on them is a full graze although I found only in English.

I'm talking about some simple control using a few commands such as date, time,

I have a microphone INMP441.

Has anyone done something like this maybe?

I will be doing. I will be basing it on HA from Whisper and Piper.