Speech Graphics Solutions Overview

Speech Graphics Technology

Speech Graphics specializes in audio-driven facial animation and related technologies, including speech models, AI-driven behavior and muscle-dynamic simulations. Speech Graphics technology works for any type of character rig, any animation style, and any language, including fictional ones. It automates full nonverbal behavior as well as accurate lip sync. Our decades-spanning research and development program involves a team of linguists, animators, AI engineers and software engineers – all focused on delivering powerful, natural and controllable facial communication at scale.

SGX

SGX is a suite of tools for producing facial animation from audio files. It includes batch processing as well as editing capabilities, character configuration editing, and multiple integrations. SGX provides animators a powerful combination of scalability, quality and control. For more information, see What is SGX?

SG Com

SG Com is a C runtime library that provides the benefits of SGX in real time on any device. It converts audio into facial animation with a latency of only 50 milliseconds on the device’s CPU. SG Com uses SGX character configurations. For more information, see What is SG Com?

Below is a comparison between SGX and SG Com animation systems.

Rapport

Rapport is an end-to-end cloud platform for deploying interactive AI-driven characters easily, on websites or in game engines. It is modular and configurable, offering developers the ability to combine the latest speech and conversational AI technologies with expressive avatars powered by SG Com. See rapport.cloud for more.