I would like to build a Google Nest mini like device.
The idea is that a Raspberry Pi Zero W with a USB microphone constantly steams the audio to a Pi 4. Pi 4 listens for a trigger word via voice2json. Once the trigger word is found, it switches to STT and sends the text to ChatGPT for interpretation.
I only can't find out how to stream audio form one Pi to another. If possible with Node Red.
Any other ideas how to solve this are welcome too.
Have a look at Johannes Kropf his node-red-contrib-voice2json node. In the examples there's a sample Audio_over_http maybe this can help you in the right direction.
Btw, not used it myself, so no experience.
Copyright OpenJS Foundation and Node-RED contributors. All rights reserved. The OpenJS Foundation has registered trademarks and uses trademarks. For a list of trademarks of the OpenJS Foundation, please see our Trademark Policy and Trademark List. Trademarks and logos not indicated on the list of OpenJS Foundation trademarks are trademarks™ or registered® trademarks of their respective holders. Use of them does not imply any affiliation with or endorsement by them.
The OpenJS Foundation | Terms of Use | Privacy Policy | OpenJS Foundation Bylaws | Trademark Policy | Trademark List | Cookie Policy