Saturday, November 7, 2026
HomeIoTKevin Lewis Goals to Tackle Face Masks Accessibility with Deepgram-Powered Speech-to-Textual content...

Kevin Lewis Goals to Tackle Face Masks Accessibility with Deepgram-Powered Speech-to-Textual content Wearable

[ad_1]

Developer advocate Kevin Lewis has leveraged Deepgram’s synthetic intelligence smarts to construct instrument designed with accessibility in thoughts — recognizing speech and changing it to textual content on a linked show for when face coverings make lip-reading unattainable.

“Masks making it onerous to know individuals both audibly or since you depend on lip studying? Simply acquired this hacked collectively,” Lewis defined whereas unveiling the system. “It shows my speech in actual time with Deepgram!”

Powered by Deepgram’s voice AI platform, for whom Lewis works as a developer advocate, the system stands alone from the masks itself. A microphone is clipped to the wearer to choose up speech, which is then transformed to textual content by way of Deepgram and the end result displayed on a display screen situated on the wearer’s chest.

“[I’m] additionally gonna make it extra wearable and fewer ‘nearly staying upright on my pocket,'” Lewis guarantees, “make [the] font larger, try to solely present my speech and never others round me, and many others. However not unhealthy for a few hours of labor.”

It is not the primary speech-to-text hack for face masks we have seen: Final 12 months maker Lorraine Underwood showcased two masks with built-in LED matrices, one powered by a Raspberry Pi single-board laptop and the opposite by an ESP32 linked to a desktop machine. In each circumstances, spoken phrases have been transformed to textual content then scrolled throughout the built-in show.

At across the similar time, Austin Nelson was displaying off an LED face masks show – although one which relied on preprogrammed messages and animations slightly than providing speech-to-text performance. Chelsea Klukas constructed one thing related a 12 months earlier, constructing within the capability to subject social distancing warnings, whereas Tyler Glaiel’s tackle the idea shows a sound-reactive animated mouth able to smiling.

Lewis hasn’t printed code for the undertaking, however will supply updates on his Twitter feed because the system is improved.



[ad_2]

RELATED ARTICLES

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Most Popular

Recent Comments