Jin10 reported on August 26 that early this morning, Microsoft Research open-sourced the innovative audio model VibeVoice-1.5B. VibeVoice-1.5B has achieved several significant technological breakthroughs in the field of speech: it can continuously synthesize ultra-realistic speech for 90 minutes in one go, while most previous models could only synthesize speech for under 60 minutes and would encounter issues such as tone drift and semantic disconnection after 30 minutes.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
Microsoft Open Source Innovation Audio Model VibeVoice-1.5B
Jin10 reported on August 26 that early this morning, Microsoft Research open-sourced the innovative audio model VibeVoice-1.5B. VibeVoice-1.5B has achieved several significant technological breakthroughs in the field of speech: it can continuously synthesize ultra-realistic speech for 90 minutes in one go, while most previous models could only synthesize speech for under 60 minutes and would encounter issues such as tone drift and semantic disconnection after 30 minutes.