Models · MarkTechPost ·
NVIDIA Releases Audex (Nemotron-Labs-Audex-30B-A3B): A Unified Audio-Text LLM That Preserves the Text Intelligence of Its Backbone
NVIDIA introduced Nemotron-Labs-Audex-30B-A3B, a unified audio-text MoE model for audio understanding, speech recognition, translation, text-to-speech, and audio generation. NVIDIA says it preserves the text capabilities of its Nemotron-Cascade-2 backbone with only minor regression.