Post-Cutoff
Search For AI agents

NVIDIANemotron Speech familyCurrentSpeech and audioReleased 3 Aug 2026

NVIDIA NemotronLabs VoiceChat 11B (and PersonaPlex-7B)

Model idnvidia/NVIDIA-NemotronLabs-VoiceChat-11B

PricePrice not published

Checked29 September 2026

Where it stands

38newer speech and audio models since its release

The 5 newest are listed. All speech and audio models

Before it from NVIDIA
NVIDIA MagpieTTS Multilingual 357M11 Dec 2025
After it from NVIDIA
NVIDIA Nemotron 3.5 Transcribe (30B-A4B)28 Oct 2026
Weights
Weights are public. Licence: OpenMDW-1.1. See the licence for commercial terms.

How to call it

3 ways to use NVIDIA NemotronLabs VoiceChat 11B (and PersonaPlex-7B), with the model id each provider expects.

Providers, model ids, endpoints and docs for NVIDIA NemotronLabs VoiceChat 11B (and PersonaPlex-7B)
ProviderModel idEndpointDocs
Hugging Face nvidia/NVIDIA-NemotronLabs-VoiceChat-11B huggingface.co
Hugging Face nvidia/personaplex-7b-v1 huggingface.co
arXiv arxiv.org

Pricing

Price not published.

No price source linked. Checked 29 September 2026.

Specs

Input
Audio
Output
Audio and text
Context window
Not published
Max output
Not published
Open weights
Yes
Licence
OpenMDW-1.1
Released
3 August 2026
Status
Current
Type
Speech and audio

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Open full-duplex speech model with tool calling

    First

    End-to-end (FastConformer encoder + Nemotron Nano v2 9B + TTS decoder, 11B total) full-duplex voice chat that calls tools mid-conversation; NVIDIA calls it the first open full-duplex model to support tool calling. BFCL-v3 (AU Harness) 56.1%, Full-Duplex-Bench v3 tool selection 82.5%.

    Source: huggingface.co

  • Natural turn-taking

    ~450 ms turn-taking latency; #2 among open models on VoiceBench and Full-Duplex-Bench 1.0 (smooth turn-taking 0.82, interruption latency 480 ms).

    Source: huggingface.co

  • PersonaPlex: persona + voice prompted full duplex

    Found after launch

    PersonaPlex-7B-v1 (2026-01-15), fine-tuned from Kyutai Moshiko, takes a voice prompt and a text persona/role prompt.

    Source: huggingface.co

Notes

English only. Requires datacenter GPU (A100/H100/H200/B100/B200 or RTX 6000). ‘First’ is NVIDIA’s claim on the model card. HF card release date 2026-08-03; arXiv paper 2609.21967 (Sept 2026).

Sources: https://huggingface.co/nvidia/NVIDIA-NemotronLabs-VoiceChat-11B , https://huggingface.co/nvidia/personaplex-7b-v1