NVIDIA NemotronLabs VoiceChat 11B v1.0
NVIDIA NemotronLabs VoiceChat is an 11B end-to-end, real-time full-duplex speech model that jointly performs streaming speech understanding and speech generation in a single architecture. It is provided as a Hugging Face checkpoint with accompanying code and supports interactive low-latency voice conversations and tool calling.
What it does
Developers and researchers can use it to build or test real-time voice assistants with speech input, speech output, and tool calling.
- Availability
- Hugging Face checkpoint with offline and interactive streaming instructions
- Pricing model
- Governed by OpenMDW License Agreement v1.1
- Deployment
- NVIDIA GPU-accelerated systems; interactive deployment via NVIDIA inference container
- Privacy
- Global deployment geography stated
- Licence
- OpenMDW License Agreement, version 1.1
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- The 11B model jointly performs streaming speech understanding and speech generation in a full-duplex architecture. [1]
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].
NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model supports tool calling during full-duplex conversation. [1]
Moreover, NVIDIA NemotronLabs VoiceChat is **the first open full-duplex model to support tool calling** while maintaining a natural conversation flow during tool execution.
NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights. - The Hugging Face checkpoint can be used for offline inference. [1]
* **Offline inference** — load this Hugging Face checkpoint for non-interactive batch speech-to-speech testing ([Offline inference](#offline-inference)).
NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights. - Interactive streaming deployment uses an NVIDIA inference container with a bidirectional WebSocket interface. [1]
* **Interactive streaming** — deploy the optimized NVIDIA inference container for real-time WebSocket conversations ([Interactive streaming deployment](#interactive-streaming-deployment)).
NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights. - The stated turn-taking latency is approximately 450 ms. [1]
- Use is governed by the OpenMDW License Agreement, version 1.1. [1]
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).
NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
NVIDIAOwner-controlled
https://huggingface.co/nvidia/NVIDIA-NemotronLabs-VoiceChat-11B
Retrieved 2026-10-28 00:39 UTC
Verified
Versions
3| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 3 | 2026-10-28 00:39 UTC | evidence update | score | Current |
| 2 | 2026-09-25 03:52 UTC | material change | capability, modality, access, deployment, pricing, availability, deployment | Current |
| 1 | 2026-07-29 17:46 UTC | publication | None | Current |
In briefs
2- DeepSeek-V4-Flash leads 3 AI developments in week 31, 2026 Weekly brief 2026-W31
- NVIDIA NemotronLabs VoiceChat 11B v1.0 from NVIDIA, the one AI development on 29 July 2026 Daily brief 2026-07-29
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.