PulseAugur
EN
LIVE 01:31:42

NVIDIA releases NemotronLabs VoiceChat 11B for real-time, full-duplex AI conversations

By PulseAugur Editorial · [2 sources] ·

NVIDIA has launched NemotronLabs VoiceChat 11B, an open-source, full-duplex speech-to-speech model designed for real-time conversational AI. This unified model integrates speech recognition, language understanding, and speech synthesis, achieving a turn-taking latency of approximately 448 ms. A key feature is its ability to perform tool calling concurrently with ongoing conversation, allowing for seamless integration of external functions without interrupting the dialogue. AI

IMPACT Enables more natural and responsive voice interactions by reducing latency and allowing concurrent tool use in conversational AI applications.

RANK_REASON NVIDIA released a new open-source model with detailed technical specifications and performance metrics. [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on Mastodon — fosstodon.org →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

NVIDIA releases NemotronLabs VoiceChat 11B for real-time, full-duplex AI conversations

COVERAGE [2]

  1. MarkTechPost TIER_1 English(EN) · Asif Razzaq ·

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

    <p>NVIDIA releases NemotronLabs VoiceChat 11B, an open full-duplex speech-to-speech model with 448 ms latency and live tool calling.</p> <p>The post <a href="https://www.marktechpost.com/2026/08/09/nvidia-releases-nemotronlabs-voicechat-11b-an-open-full-duplex-speech-to-speech-mo…

  2. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    NVIDIA has released NemotronLabs VoiceChat 11B, an open full-duplex speech-to-speech model with 448ms turn-taking latency. The model processes speech continuous

    NVIDIA has released NemotronLabs VoiceChat 11B, an open full-duplex speech-to-speech model with 448ms turn-taking latency. The model processes speech continuously without chaining separate components, enabling real-time conversation with tool calling capabilities. https://www. ma…

RELATED ENTITIES

RELATED TOPICS