Visualize human speech with

We are thrilled to announce AuditoryAR, a geospatial speech inference and display system powered by Artificial Intelligence!


What can AuditoryAR do?

AuditoryAR was developed as a visual aid for the hard-of-hearing. It analyzes real-time speech and displays it near the point of origin in an AR environment.

Some other features include:


By analyzing similar voice intonations, voices belonging to different people will be matched and displayed differently

Geospatial Positioning

Places text near the origin of a sound in your 3D environment, providing visual aid in identifying sources of audio

Computer Vision

With OpenCV and visual data from AR, displays an audio source consistently with a specific object in the world