Full-Duplex Voice AI Needs a New ArchitectureOriginalThe PACE paper exposes a fundamental flaw in LLM voice dialogue: the model sees context the user never heard. Full-duplex voice needs a new architecture, not just faster TTS.Voice AI
WebSocket vs REST TTS APIs for Voice AgentsOriginalChoosing between WebSocket and REST for your streaming TTS API changes your voice agent's latency floor. Here is how to pick the right protocol.TTS