Wispr Flow - Don’t type, just speak
Mini toolsPhoenix 2
By Tavus
Phoenix-2 is presented as an evolution of Phoenix that replaces the earlier NeRF backbone with 3D Gaussian Splatting, using learned audio-driven 3D facial deformation plus fast rendering to better support real-time, high quality avatar animation and novel view synthesis from unseen audio.
Video
Gen 4
Overview
Phoenix-2 is Tavus’ next Phoenix research model that shifts the avatar rendering backbone toward 3D Gaussian Splatting to improve speed and controllability for talking head generation.
Tools using Phoenix 2
-
Patrice Blanchard🙏 13 karmaSep 19, 2024@TavusThe demo of this AI zagent is pretty stunning. The agent understand what I am saying zand is replying on the spot. Very interesting. The sky seems to be the limit. But how can a small company use this kind of tool in practice.
Last updated: April 6, 2026
