Voice Agents from First Principles
How a machine hears you, decides you're done, understands you, thinks and answers out loud. Samples, turn-taking, speech recognition, agents and speech synthesis, built up byte by byte.
I want to build a voice app where someone practises a difficult conversation with an AI role-play partner. That only works if I understand every layer underneath, especially silence and timing, so this track is general: no product, no vendor, just how it works.