Moshi (Kyutai)
Open-source speech-to-speech model
Episodes
-
#2512: How Speech-to-Speech Models Eliminate the Robot VoiceWhy AI voice agents sound robotic, and how natively integrated speech-to-speech models fix it. -
#1546: The Death of Latency: Three Pillars of Modern Voice AISay goodbye to the "digital sandwich." Explore the three architectural pillars closing the latency gap in modern speech recognition.