Preview 1
Course Contract: Engineer the Conversation, Not a Talking Demo
A voice agent is a realtime media system, an AI application, and an authority boundary at once.
Conversational Systems Track
Engineer low-latency voice sessions across WebRTC, SIP, streaming speech, turn-taking, interruption, tools, RAG, handoff, evaluation, consent, safety, scaling, and incident operations.
Before you start: HTTP, asynchronous events, cancellation, and the basic model request path.
Plan for 6–10 hours of hands-on work in addition to reading. This is an initial estimate; setup and extensions vary.
Open before purchase
Read these complete sections to judge the technical depth, teaching style, and architecture standard before buying.
Preview 1
A voice agent is a realtime media system, an AI application, and an authority boundary at once.
Preview 2
Speech models receive sampled pressure changes, not words.
Preview 3
The model is one dependency inside capture, media, state, action, and policy layers.
Complete curriculum