NVIDIA Releases Open-Source Audio-Text LLM Audex-30B
NVIDIA has officially released Nemotron-Labs-Audex-30B-A3B (Audex), an open-source unified audio-text Large Language Model. Designed to process both audio and text simultaneously within a single architecture, the model addresses the intelligent bottlenecks of traditional audio models in multimodal fusion, marking a significant advancement in multimodal AI.
Architecture and Core Capabilities
Audex utilizes a Mixture-of-Experts (MoE) architecture with a total of 30B parameters but only activates 3B parameters during inference. By sharing a transformer decoder, the model projects audio inputs into the text embedding space to integrate audio and text processing. This design allows it to natively support full-stack tasks including audio understanding, speech recognition and translation, text-to-speech, audio generation, and speech-to-speech generation, while supporting SFT and RL training.
Performance and Industry Reception
NVIDIA emphasizes that Audex achieves "audio intelligence without sacrificing text intelligence." It achieved state-of-the-art performance among open-source models on multiple audio intelligence benchmarks, while also outperforming text-only models in math, code reasoning, alignment, and instruction following. Developer @andrew_n_carr noted that while many audio models lack common sense, Audex demonstrates stronger comprehension, potentially making it the first native audio model that is "not so dumb."
2026-07-07 ~ 2026-07-09 · 9 related posts
- NVIDIA Releases Audex-30B-A3B Audio Language Model — nvidia · 2026-07-07
- [source] Nvidia Launches Nemotron-Audex-30B: Unified Audio-Text LLM — pmttyji · 2026-07-07
- NVIDIA Proposes Unified Audio-Text Large Language Model — nvidia · 2026-07-07
- NVIDIA Releases Audex: Unified Audio-Text MoE Model — ctnzr · 2026-07-07
- [source] Audex: Open-Source Audio-Text LLM with Leading Multimodal Capabilities — _weiping · 2026-07-08
- NVIDIA Releases Audex Audio Language Model — _weiping · 2026-07-08
- Nvidia Releases Native Audio Model — andrew_n_carr · 2026-07-09