Acerca de
This skill empowers Claude to act as a production-level voice AI architect, specializing in designing conversational interfaces that feel natural and responsive. It provides deep technical guidance on choosing between Speech-to-Speech (S2S) models and modular STT-LLM-TTS pipelines, with a heavy emphasis on managing the 'physics of latency' to keep response times under 800ms. Users can leverage this skill to implement critical features like Voice Activity Detection (VAD), barge-in handling, and emotional nuance while avoiding common pitfalls like excessive response length or poor jitter management.
