Not sure how feasible that would be or if this already is the case, I'm guessing it isn't because there is the need for setapp ai credits or to use my OpenAI Api Key, for the more privacy conscious or that deals with trade secrets in business meetings having an option for Spellar spin up an optimized tiny model to run the transcription and summarization at the local machine too would be great. That could be a separate cheaper tier.

One would save the recordings and could start processing at a time the machine would idle for one reason or the other and do all the processing locally.