As promised, here is the GitHub link for my 100% local voice-to-voice assistant

I've posted up earlier versions of this project before, promising a GitHub link, but never got around to pushing the code from my local system. Sorry all, I have a very busy life :P Anyway, without further ado: GitHub: github.com/igorbarshteyn/athena Athena is a fully offline, privacy-first voice assistant that runs entirely on local hardware. Athena combines a large mixture-of-experts language model (Qwen3.5-397B), neural text-to-speech (Orpheus 3B), real-time speech recognition (Whisper-small.en),