AI Matters

Why it matters

NVIDIA releases open-source real-time voice model

MarkTechPost NVIDIA Releases NemotronLabs VoiceChat 11B: An Open Full-Duplex Speech-to-Speech Model with ~450 ms Turn-Taking and Live Tool Calling

NVIDIA released NemotronLabs VoiceChat 11B, an open-source speech-to-speech model with 450-millisecond latency and live tool-calling support.

Why it matters

Developers can build ultra-low-latency voice assistants that can interrupt, take turns naturally, and call external tools during a call.