Davit @Krisp@davitbMay 7, 2026
New voice isolation, turn detection, turn prediction, and speech classification signals models from Krisp!
Krisp's fast, dedicated functionality audio models are mainstays of production voice agents.
I recently helped the AWS team set up live voice agent demos for their big booth at the NVIDIA GTC conference. A huge, noisy conference expo floor is the hardest environment possible for live voice demos. We used the Krisp VIVA voice isolation model (running on Pipecat Cloud). Lots of background speech of all kinds. No problem! The massive venue sound system cranking k-pop every hour on the hour. No problem!
Congratulations to the Krisp team on this release. Thanks for the fantastic models.
Davit @Krisp@davitbWe just shipped VIVA 2.0 at @krispHQ — launching live at @twilio Signal in SF.
8 years. A trillion minutes of real-world voice. This is what it all built toward.
Voice Infrastructure for Voice AI Agents 🧵
