“Toward Fluid AI Conversation with Natural Turn-taking: Full-duplex Modeling with Audio Codec LMs” Channel: Tetherless World164 views • 11/11/2025Related VideosNeural audio codecs: how to get audio into LLMsLLM-CODEC: How AI Listens"Moshi: a speech-text foundation model for real-time dialogue" - Alexandre DéfossezSpeech LLMs: Models that listen and talk back
