Speech-Based AI
Moshi is a groundbreaking speech-based foundation model designed for fluid, real-time dialogue, allowing for full duplex communication. With an impressive latency of just 200 milliseconds, it offers a seamless conversational experience. The team behind Moshi recognized the potential of combining advanced audio modeling with text knowledge, positioning themselves ahead of the competition in the evolving landscape of speech technology.In this clip
From this podcast
Practical AI
Full-duplex, real-time dialogue with Kyutai
Related Questions