On-premise deployment means running the AI Avatar model on servers in your own data centre or location, instead of in the vendor's cloud. Conversation audio and video stay on hardware you control, which suits regulated industries, sites with strict security rules and kiosks in physical locations.
The vendor supplies the model and software; your team runs it on your own GPU servers, inside your network and security controls. Your IT team decides how the system is monitored, updated and connected to other systems.
The main question is hardware. How efficiently the model renders decides how many GPUs you need for your peak number of conversations, so ask vendors for sessions per GPU at your target resolution.
Beyond Presence offers Genesis 2.0 on-prem, as well as in its EU cloud and in your private cloud. One entry-level NVIDIA GPU runs 12 live 1080p Avatars, which keeps hardware small. One of the largest Italian electronics chains runs Beyond Presence Avatars on in-store kiosks on-prem. See enterprise deployment options.
Yes. Genesis 2.0 runs on servers in your own data centre, as well as in the Beyond Presence EU cloud or your private cloud.
GPU servers. One entry-level NVIDIA GPU runs 12 live 1080p Avatars, so size for your busiest hour.
One of the largest Italian electronics chains runs Beyond Presence Avatars on in-store kiosks, on-prem.