Unspokn
About this project
In one sentence, what are you building?
Unspokn is an AI-powered communication app that translates silent lip movements into text or natural-sounding speech, giving everyone a way to communicate without making a sound.
What problem are you solving?
Millions of people face barriers to spoken communication, whether because of speech disabilities, temporary voice loss, or environments where speaking aloud isn't possible or desirable. Existing speech-to-text tools require audible speech, while many assistive communication solutions rely on typing, selecting predefined phrases, or specialized hardware. These approaches can be slow, inconvenient, or inaccessible in everyday conversations. Unspokn introduces a camera-first alternative. Using open-source visual speech recognition models, it interprets silent mouth movements and generates editable text that users can display, share, or convert into natural-sounding speech using Deepgram. We're building Unspokn for web and mobile, with privacy, accessibility, and user control at its core. Our vision is to make communication more inclusive by giving people another way to express themselves—without requiring them to speak aloud.