← Back to Model Beat
Products·1d ago·all news from September 21, 2026

NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities

NemotronLabs VoiceChat is a new open-source model designed for full-duplex, speech-to-speech interaction with native tool-calling capabilities. By integrating a streaming speech encoder directly with a decoder-only language model, the system enables real-time spoken communication and the ability to execute external tasks. This development provides developers with an alternative for building voice-driven AI agents that can process audio input and output simultaneously while interacting with digital tools.

Covered by 1 source

  • AarXiv CS.AIJagadeesh Balam, Travis Bartley, Edresson Casanova, Sanjay Chauhan, Chen Chen, Zhehuai Chen, Zijia Chen, Francesco Ciannella, Slyne Deng, Mikyas Desta, Harishchandra Dubey, Slim Essid, Nourchene Ferchichi, Boris Ginsburg, Mariana Graterol Fuenmayor, Negar Habibi, Kevin Hu, Anand Joseph, Viraj Karandikar, Myungjong Kim, Viacheslav Klimkov, Seelan Lakshmi Narasimhan, Lily Lee, Jason Li, Eileen Long, Ameya Mahabaleshwarkar, Aditya Malte, Adi Margolin, Sasha Meister, Valentin Mendelev, Oluwatobi Olabiyi, Ankita Pasad, Yifan Peng, Elena Rastorgueva, Jayda Ritchie, Jason Roche, Nikhil Srihari, Yuanhang Su, Yoshi Suhara, Viet Anh Trinh, Jinhan Wang, Piotr Zelasko, Hui Wang, Puhui Meng, Chaosen Zhang, Yunsheng Liu, Shawn Wang, Wenjing Li, Zhonglei He1d ago

Related stories

ProductsMeta’s New Muse AI App Tops Charts, Draws Strong Early ReviewsSep 17 · 8 sourcesProductsAmazon blocks Meta's AI agent Muse from online shoppingSep 21 · 6 sourcesProductsAI training built on fair use looks shaky when the companies' own people call it "astonishing theft"Sep 17 · 8 sourcesProductsGoogle Rolls Out $899-Plus Googlebooks from Dell, HP, Lenovo, Acer, ASUSSep 21 · 5 sources