nvidia/NVIDIA-NemotronLabs-VoiceChat-11B

NVIDIA NemotronLabs VoiceChat 11B

▶ Hear it first. Natural turn-taking, barge-in and live tool calling.

| Sample | What to listen for | Player | |---|---|---| | Natural turn-taking | Smooth back-and-forth, ~450 ms response | | | Barge-in / interruption | User cuts in; model yields instantly | | | Tool calling live | Tools are called when needed | |

▶ Code: On Github

Model Overview

Description:

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]. Unlike traditional cascaded stacks (ASR → LLM → TTS), this model achieves full duplex, real-time, seamless voice interaction in one unified architecture, eliminating the need for multiple models or API handoffs, thus reducing end-to-end latency. It sets new benchmarks by bringing open, robust, and highly natural conversation capabilities. Moreover, NVIDIA NemotronLabs VoiceChat is the first open full-duplex model to support tool calling while maintaining a natural conversation flow during tool execution. For each tool, a specific “on-hold” message can be defined that will be spoken by the agent as soon as the LLM generates the text that will trigger the tool call and response.

The model operates on audio signals, which are encoded using a fast conformer module. The resulting audio tokens are inputted into a Nemotron Nano V2 9B LLM backbone to predict text tokens, which are fed to a TTS decoder [2] to predict audio codes for generating the agent's speech. A separate output channel is used to predict tool calling scripts. NemotronLabs VoiceChat offers an unprecedented trade-off between intelligence and latency in the space of open-source voice agents, as highlighted by our benchmarking results [below](#testingevaluation-dataset).

> This model is ready for research purposes only.

Highlights

| Parameters | Turn-taking latency | VoiceBench (open FD) | Tool calling | Architecture | |---|---|---|---|---| | 11B | ~450 ms | #2 | 1st open FD | 1 unified model |

License/Terms of Use

GOVERNING TERMS: The use of this model is governed by the OpenMDW License Agreement, version 1.1.

Use Case:

NemotronLabs VoiceChat is targeted for researchers, developers, and professionals in the field of natural language processing (NLP) and speech technology for purposes such as automatic speech recognition (ASR), text-to-speech synthesis (TTS), and voice assistant development.

Deployment Geography

Global

Release Date:

August 3, 2026.

Model Architecture

Architecture Type: Hybrid Mamba/Transformer · Parameters: 11B

Network Architecture:

NemotronLabs VoiceChat uses:

• Fast Conformer Speech Encoder from Nemotron-Speech-Streaming-En-0.6b
• NVIDIA Nemotron Nano v2 LLM backbone
• NVIDIA TTS decoder and codec [3]
• Separate output channel for tool-calling scripts


Input

| Property | Value | |---|---| | Input Type(s) | Text (prompt), Audio (user speech) | | Input Format | String, WAV/WebAudio | | Sample rate | 16 kHz |

Output

| Property | Value | |---|---| | Output Type(s) | Text (agent), Audio (agent speech), Text (user transcription) | | Output Format | String, WAV/WebAudio | | Sample rate | 22.05 kHz |

How NemotronLabs VoiceChat Compares to Other Open FD Models

| Model | Params | Tool calling | |---|---|---| | NemotronLabs VoiceChat | 11B | ✔ | | PersonaPlex 7B | 7B | ✘ | | Moshi | 7B | ✘ | | Freeze-Omni | 7B | ✘ |

Software Integration

Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.

Runtime Engine: vLLM

Supported Hardware Microarchitecture Compatibility:

• NVIDIA A100
• NVIDIA H100
• NVIDIA H200
• NVIDIA B100
• NVIDIA B200
• NVIDIA RTX-6000

Preferred/Supported Operating System(s):

• Linux

The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.

Model Version(s)

• v1.0

Quickstart

To try inference with the model, check the instructions below:

• Offline inference — load this Hugging Face checkpoint for non-interactive batch speech-to-speech testing ([Offline inference](#offline-inference)).
• Interactive streaming — deploy the optimized NVIDIA inference container for real-time WebSocket conversations ([Interactive streaming deployment](#interactive-streaming-deployment)).

Full setup details are also availabel in the Github repo.

Training, Testing, and Evaluation Datasets:

Training Dataset:

Data Modality: Audio (speech) and Text

Audio Training Data Size: ~550k hours

VoiceChat has been trained on a blend of different datasets comprising both real audio datasets and synthetic speech datasets generated using various TTS systems on text training corpora, including:

• Nemotron 5.5 pre-training and SFT text data
• Brainy-mantis text data
• Greteal AI v1 and v2 text data
• Ultrachat text data
• Blackwell studio recordings real speech data
• Fisher real speech data
• LibriVox
• LibriTTS
• HiFi-TTS
• Riva Speakers: Internal Dataset
• Publicly available internet scale data
• PromptTTS
• VCTK
• Voxmovies
• JL-Corpus
• Nemotron...