video1.0<iframe src="https://www.loom.com/embed/eb44015201554d11ac841cd1700653ce" frameborder="0" width="1220" height="915" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>9151220Loomhttps://www.loom.com9151220https://cdn.loom.com/sessions/thumbnails/eb44015201554d11ac841cd1700653ce-1e812004e9bff2a0.gif102.605An unscripted conversation with y30, the voice AI I'm building for older adults and their caregivers. The thing to watch is the turn-taking: it waits through a long mid-thought pause without cutting in, and yields the instant I interrupt it. When the conversation turns to my late mother, it softens its tone on its own. Under the hood it's a streaming speech-to-text to LLM to text-to-speech pipeline with deterministic flow control and a safety floor that runs independent of any model, every conversation becomes structured signal a caregiver can act on. Part of my portfolio: whoischrislam.github.io