Voice Agent Engineering — Nik Caryotakis, SuperDial
Apr 18, 2025 · 19:07
Nik Caryotakis from SuperDial argues that in 2025, the key to production Voice AI is reliability over realism, especially for sensitive healthcare calls. SuperDial automates back-office phone calls, saving over 100,000 hours of human calling with a lean team of four engineers. He advocates for the 'say the right thing at the right time' approach, using open-source tools like PipeCat for orchestration, TensorZero for LLM routing, and self-hosted LangFuse for HIPAA-compliant observability. Caryotakis warns that new voice-to-voice models often produce nonsensical audio, favoring a sequenced STT/LLM/TTS pipeline for control. He shares specific last-mile challenges: pronunciation of names like 'Caryotaikis', avoiding confusing bot names like 'Billy', and the need for fallbacks when OpenAI goes down. The talk emphasizes that the unique value of a voice agent lies in conversational design and vertical integrations, not realistic voices.
