6h agoIvan Fioravanti builds a local llama.cpp voice pipeline for Reachy Mini that requires artificial delays to prevent interrupting humansThe system runs on Apple's M5 chip using Gemma.SentimentSentimentPos100%Neg0%Many users are excited about Hugging Face's open-source realtime API for local AI conversations on the Reachy Mini robot because they find the modular voice setup incredibly cool, fun, and practical to run themselves.18 comments with sentiment. View comments.