Lates News

This morning, Microsoft Research Institute open-sourced the innovative audio model VibeVoice-1.5B. VibeVoice-1.5B has made several significant technological breakthroughs in the field of speech: it can continuously synthesize up to 90 minutes of ultra-realistic speech in a single session, whereas most models can only synthesize speech for up to 60 minutes and encounter challenges such as voice drift and semantic disconnection after 30 minutes.