{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T15:45:30.655Z","data":{"recordId":"wsa_nwteive8u4zc","score":0.95,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/nvidia/NVIDIA-NemotronLabs-VoiceChat-11B","publisher":"NVIDIA","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-28T00:39:38.860Z","detectedPublishedAt":"2026-07-29T17:46:48.000Z","rights":"original"}],"claims":[{"id":"f742dd21-efe6-442a-bc48-bc2652d8f150","kind":"capability","statement":"The 11B model jointly performs streaming speech understanding and speech generation in a full-duplex architecture.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"NVIDIA NemotronLabs VoiceChat is a **11B end-to-end, real-time speech full duplex (FD)** model for conversational AI that jointly performs streaming speech understanding and speech generation [1, 2, 3].","rights":"original"}}]},{"id":"c6d3a94d-9a02-404e-a8f0-f7b70a70561b","kind":"capability","statement":"The model supports tool calling during full-duplex conversation.","citations":[{"source":1,"supportProbability":0.96,"supports":true,"quote":{"text":"Moreover, NVIDIA NemotronLabs VoiceChat is **the first open full-duplex model to support tool calling** while maintaining a natural conversation flow during tool execution.","rights":"original"}}]},{"id":"3dc3e985-d5ec-4889-a3a5-b1e251f692a9","kind":"availability","statement":"The Hugging Face checkpoint can be used for offline inference.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"* **Offline inference** — load this Hugging Face checkpoint for non-interactive batch speech-to-speech testing ([Offline inference](#offline-inference)).","rights":"original"}}]},{"id":"ae552b47-85d2-49bb-9c92-9a5e9f08f351","kind":"availability","statement":"Interactive streaming deployment uses an NVIDIA inference container with a bidirectional WebSocket interface.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"* **Interactive streaming** — deploy the optimized NVIDIA inference container for real-time WebSocket conversations ([Interactive streaming deployment](#interactive-streaming-deployment)).","rights":"original"}}]},{"id":"52bb0eb0-bafd-48d1-9815-9d8893159475","kind":"recommendation-relevant","statement":"The stated turn-taking latency is approximately 450 ms.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":null}]},{"id":"528863f2-9b22-4a17-b185-c2f9c1a19b41","kind":"pricing","statement":"Use is governed by the OpenMDW License Agreement, version 1.1.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"GOVERNING TERMS:  The use of this model is governed by the [OpenMDW License Agreement, version 1.1](https://github.com/OpenMDW/OpenMDW/blob/main/1.1/LICENSE.OpenMDW-1.1).","rights":"original"}}]}]},"nextCursor":null,"license":{"catalog":{"name":"CC BY 4.0","spdx":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"wowsuchai","attributionUrl":"https://wowsuchai.withglint.app","covers":["catalog metadata","classifications","generated summaries","feed event metadata"]},"excluded":{"covers":["source quotations","linked source content"],"terms":"Not licensed by wowsuchai. Source quotations and linked source content keep their original rights."}}}