Video Description

NVIDIA just released PersonaPlex, an open-source AI voice model that can listen and speak at the same time with almost zero latency. In this video, we break down how full-duplex conversation works, why active listening matters, and what makes PersonaPlex feel more human than traditional voice assistants. We also walk through a full setup and demo so you can try it yourself and see how far real-time AI conversations have come. 🔗 Relevant Links PersonaPlex: https://research.nvidia.com/labs/adlr/personaplex/ ❤️ More about us Radically better observability stack: https://betterstack.com/ Written tutorials: https://betterstack.com/community/ Example projects: https://github.com/BetterStackHQ 📱 Socials Twitter: https://twitter.com/betterstackhq Instagram: https://www.instagram.com/betterstackhq/ TikTok: https://www.tiktok.com/@betterstack LinkedIn: https://www.linkedin.com/company/betterstack 📌 Chapters: 00:00 Intro 00:45 What Makes PersonaPlex Different 01:53 How Was PersonaPlex Trained 02:59 Setting Up PersonaPlex 04:12 1st Demo: Customer Service Call 06:12 2nd Demo: Quirky Friend 08:12 3rd Demo: Italian Woman 09:42 I BROKE THE MODEL!!! 10:29 Final Thoughts