← Back to Model Beat
Models·Aug 9·all news from August 9, 2026

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

NVIDIA has released NemotronLabs VoiceChat 11B, an open-source model capable of full-duplex speech-to-speech interaction. The system features a turn-taking latency of approximately 450 milliseconds and supports real-time tool calling during conversations.

Covered by 1 source

Related stories

ModelsIntroducing Gemini 3.7 FlashAug 11 · 13 sourcesModelsDeepSeek Jacks Up Price for Flagship AI Models Ahead of IPOAug 10 · 34 sourcesModelsAlibaba AI Models Hit 3 Billion Downloads, Passing Meta, GoogleAug 13 · 32 sourcesModelsMeta is back with Muse Glimmer: local, agentic, multimodal, and open sourceAug 10 · 31 sources