Hi all,
Im looking for a place to start regarding a project im building.
I want to do something like this:
https://www.draw.io/?lightbox=1&highlig ... eqm1bqo0Jl
The idea is that the RPI will be plugged in to the headset jack on a smartphone and then listen to the audio stream on phone calls. The audio from the phone call will then be processed and converted in to text. The text will then trigger a specific answer that is streamed back through the microphone to the smartphone.
Now im fully aware of all the cloud based services that can handle the speech to text and text to speech part, so no pointers needed there.
Im only looking for some pointers on wether it is possible to so and if someone have experience with something similar.
Thanks