Access to digital content remains a significant challenge for the deaf and hard of hearing community. Many online videos, whether educational, entertainment, or informational, rely heavily on spoken language, which can be inaccessible to individuals who are deaf or hard of hearing. Traditional solutions such as subtitles and closed captions are often limited in their effectiveness. They may not always accurately capture the nuances of spoken dialogue, and not all videos include these features. Additionally, existing captioning solutions do not provide real-time translation into sign language, which is essential for effective communication for those who use American Sign Language (ASL) or Indian Sign Language (ISL).

Our project addresses this issue by developing a browser extension that extracts audio from online videos, converts it into text, and translates this text into corresponding ASL or ISL gestures. This real-time translation enables deaf and hard of hearing viewers to access video content more intuitively and naturally. The use of gesture images as an interim solution will provide immediate benefits, while future enhancements will integrate dynamic 3D models for a more immersive experience. By bridging the gap between spoken language and sign language, our solution ensures that digital content is more inclusive and accessible, fostering greater participation and engagement from the deaf community. This innovative approach not only addresses the limitations of traditional captioning but also sets a new standard for digital accessibility.