alt Hacker NewsIf there is a small model that can run on a low powered device you might be able to use that too so that it is all self contained.
It will think (generate tokens) throughout the day, then convert that to voice and save it and will keep generating so on. Every time it is poked, it will play one of the saved recordings.
Someone else suggested Gemma E2B which I can run on Ollama def going to try that next. I can also write a lil cronjob to have it wake up and do things on its own then wire up the button to kick off a function that starts the voice mode. I’ve found local models sometimes struggle with tool usage though. Fun direction to try next. Thanks!