NVIDIA Releases Audex (Nemotron-Labs-Audex-30B-A3B): A Unified Audio-Text LLM That Preserves the Text Intelligence of Its Backbone

NVIDIA has introduced Audex, a 30-billion parameter mixture-of-experts model designed to unify audio understanding, speech recognition, translation, and text-to-speech generation. By utilizing the existing Nemotron-Cascade-2 architecture, the model maintains high-level text processing capabilities while expanding functionality into multifaceted audio tasks.