TLDRocket
Sign in

NVIDIA released open-weight speech-to-speech and multilingual text-to-speech models for low-latency voice agents

Product launch Provisional 56% confidence first seen

NVIDIA published NemotronLabs VoiceChat 11B, an open end-to-end full-duplex speech-to-speech model positioned for real-time turn-taking and live tool calling, with research-only availability requiring substantial GPU resources. Separately, NVIDIA released Magpie multilingual text-to-speech updates (with additional languages) and an accompanying NIM serving stack aimed at low-latency voice-agent deployments under developers’ infrastructure.

Magpie Multilingual TTS NVIDIA NemotronLabs VoiceChat 11B Brazilian Portuguese Full-Duplex-Bench 1.0 Korean MarkTechPost Modern Standard Arabic NIM NVIDIA B200

Source coverage

NVIDIA Releases NemotronLabs VoiceChat 11B: An Open Full-Duplex Speech-to-Speech Model with ~450 ms Turn-Taking and Live Tool Calling MarkTechPost Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS Hugging Face official

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.