One Open Source Project a Day (No.51): VibeVoice - Microsoft's Speech AI That Processes 90 Minutes of Audio in a Single

Introduction "The fundamental limit of traditional speech AI isn't model quality — it's architecture. They were never designed for long audio." This is article No.51 in the "One Open Source Project a Day" series. Today's project is VibeVoice ( GitHub ). In August 2025, Microsoft Research quietly pushed a repository to GitHub. No launch event. No press release. The capability it demonstrated: synthesizing 90 minutes of natural multi-speaker conversation — 4 speakers, consistent voices throughout