Get Started

Streaming Speech-to-Speech, Moshi, Hibiki, and Full-Duplex Dialogue

2024-2026 redefined voice AI. Moshi ships a single model that listens and speaks simultaneously at 200 ms latency. Hibiki does speech-to-speech translation chunk-by-chunk. Both abandon the ASR → LLM → TTS pipeline for a unified full-duplex architecture over Mimi codec tokens. This is the new reference design.

75 minutesLearnPythonMembers