Tech Feb 4, 2026 3 min ACE-Step 1.5: AI Music Generation Gets a Full Architecture Overhaul ACE-Step V1.5 has been released with a hybrid LM+DiT architecture, 50+ language support, and 4GB VRAM minimum — a major evolution from V1.0. AI Audio Generation Local LLM
Tech Feb 3, 2026 4 min MOVA: the first open-source model that generates video and audio together MOVA-720p from the OpenMOSS team is an open-source model that generates video and audio in a single pass. This article covers how it differs from closed models like Vidu Q3 and what its architecture looks like. AI Video Generation Audio Generation Open Source
