Models · MarkTechPost ·

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

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 full-duplex speech-to-speech model. It supports live tool calling and reports approximately 448 milliseconds of turn-taking latency.

Read the full story at MarkTechPost →