# NVIDIA's Audex Unifies Audio Understanding and Speech

> A new 30B mixture-of-experts model from NVIDIA handles both listening and speaking within a single audio-text architecture.

Published by The Open Weights on Jul 6, 2026. Canonical: https://theopenweights.com/news/nemotron-labs-audex-30b-a3b-qo1w

## Key facts

- Company: NVIDIA
- Model: Nemotron-Labs-Audex-30B-A3B
- Version: 1
- Category: Any-to-Any
- Modalities: Any-to-Any, Text → Speech, Reasoning
- License: Other (Open weights, commercial use allowed)
- Parameters: 30B (mixture of experts)
- Active parameters: 3B
- Context window: 1.0M tokens
- Architecture: nemotron_labs_audex
- Significance: notable
- Published: 2026-07-06
- Last verified: 2026-07-18
- Hugging Face: https://huggingface.co/nvidia/Nemotron-Labs-Audex-30B-A3B
- Canonical URL: https://theopenweights.com/news/nemotron-labs-audex-30b-a3b-qo1w

NVIDIA has released **Nemotron-Labs-Audex-30B-A3B**, a mixture-of-experts model that folds audio understanding and speech generation into a single system. According to the model's [Hugging Face page](https://huggingface.co/nvidia/Nemotron-Labs-Audex-30B-A3B), it is designed as a unified audio-text architecture — able to both interpret incoming audio and produce speech, rather than splitting those jobs across separate specialized models.

The model uses a mixture-of-experts design with roughly 30 billion total parameters but only about 3 billion active per token, the arrangement its "30B-A3B" name signals. That approach keeps inference costs closer to a small dense model while giving the network a larger pool of specialized capacity to draw from, a pattern NVIDIA and others have leaned on across recent Nemotron releases.

## Why it matters

Most production audio stacks still chain together distinct components — a speech recognizer, a language model, and a separate text-to-speech engine. A single model spanning both comprehension and generation could simplify those pipelines and reduce the latency and error accumulation that comes from stitching parts together.

- Unified audio-text handling for both understanding and speech synthesis
- Mixture-of-experts efficiency: ~30B total, ~3B active parameters
- Reasoning listed among its capabilities alongside audio and TTS

The release ships under a custom NVIDIA license rather than a standard open-source one, so teams will want to check the terms before building on it. As an initial version, Audex sets a baseline for a family that NVIDIA appears positioned to iterate on.

## Get the model

- [Hugging Face](https://huggingface.co/nvidia/Nemotron-Labs-Audex-30B-A3B)

## Sources

- [nvidia/Nemotron-Labs-Audex-30B-A3B](https://huggingface.co/nvidia/Nemotron-Labs-Audex-30B-A3B) — Hugging Face, Jul 6, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "NVIDIA's Audex Unifies Audio Understanding and Speech", The Open Weights, Jul 6, 2026, https://theopenweights.com/news/nemotron-labs-audex-30b-a3b-qo1w