Guillaume-slize
commented
2 years ago For those who are interested, the way we implemented it was: 1 - by registering several nodes through the add_key.py script (I originally did not pay attention to the number of character for the key, and it took some time before I realised I was over and under 16 characters!). 2 - using the web speech API (https://developer.mozilla.org/en-US/docs/Web/API/Web_Speech_API/Using_the_Web_Speech_API) to get text to speech. This was done directly in the htlm file through javascript.
We managed to create a flask running on a private server with our own customised skills (http://www.tropozone.guillaumeslizewicz.com:8081/general ), we would like to build on it and allow people to interact with it via voice. We checked @ccoreilly implementation of hivemind for his catalan voice assistant but we're not sure where to start. 1- What would be the best way to create a new node every time someone connect to the page? 2- How could we implement tts and stt? (we've seen Ciaran use Festival and Vosk, would you recommend these options?) Many thanks :)