App uses Avatars to translate speech into Kenyan sign language

A young Kenyan entrepreneur is harnessing AI to break communication barriers for the deaf community. His web app, Terp 360, aims to become Africa’s first sign language translation platform built for local use. Signvrse’s Terp 360 claims to be Africa’s first AI translation platform built specifically for local use. It translates text and speech into Kenyan Sign Language through avatars, enhancing communication for both deaf and hearing individuals. “We like to call it Google Translate for sign language—and how this works is it interprets text and speech input and outputs very fluid natural avatars, which is a digital human that now signs the same way a human being does at scale,” explains Elly Savatia, the 24-year-old founder of Signvrse. Founded in 2023 and a recipient of the Kenya Presidential Innovation Award, Signvrse is on a mission to digitize Kenyan Sign Language by using motion capture systems to accurately record sign language motion from real interpreters. The combination of body movement, hand rotation and articulation, and facial expressions allows the application to accurately capture the linguistic and vibrant nature of sign language. Eventually, the company hopes the solution can be used in both business and personal contexts through a subscription. For the deaf community, it could be a very helpful solution to the challenges of daily life. “I had a lot of challenges when searching for a job, and sometimes when I go to hospital, I have a lot of challenges,” says Kelvin Munene, a deaf waiter working in Nairobi. “I think when using this app, it will help those challenges and it will make communication easier,” he adds. However, he says he hopes the application can one day use both English and Kiswahili. Leakey Nyabaro, a member of the deaf community and the founder and director of Galaxy Sign Language Training Centre in Kenya, says, “We find that there are a lot of errors. It’s not that perfect, but somehow I find it more effective when it is sign-to-voice (translation). We find that it is voiced correctly, benefiting more of the hearing community but not the deaf.” This article was provided by The Associated Press.