What is YouDescribe?
YouDescribe is a community-powered platform that makes online videos accessible to blind and low-vision (BLV) users through audio description. Volunteers use built-in tools to narrate key visual elements in YouTube and TikTok videos, expanding access to entertainment, education, and culture.
Launched in 2013 as a crowdsourced solution, YouDescribe enables anyone to contribute spoken narration to online videos. By 2022, its global community had created over 6,400 audio-described videos. However, as the volume of video content continues to grow, a volunteer-only approach is no longer sufficient to meet demand.
In response, the 2025 update introduced AI-generated description drafts integrated into a Human in the Loop (HITL) framework. This hybrid model combines machine-generated suggestions with human refinement, allowing contributors to produce high-quality, context-rich descriptions more efficiently. YouDescribe now offers a scalable and inclusive model for accessible media that preserves both quality and human insight.
Inside YouDescribe
Most Recent Publications
- Lana Do, Sanjay Mirani, Charity Pitcher-Cooper, Xuan Duy Anh Nguyen, Alekya Bairaboina, and Ilmi Yoon. 2025. YouDescribe: Bridging AI Efficiency and Human Insight for Scalable Audio Description. In Adjunct Proceedings of the 4th Annual Symposium on Human-Computer Interaction for Work (CHIWORK ’25 Adjunct). Association for Computing Machinery, New York, NY, USA, Article 10, 1–7.
- Pitcher-Cooper C, Seth M, Kao B, Coughlan JM, Yoon I. You Described, We Archived: A Rich Audio Description Dataset. J Technol Pers Disabil. 2023;11:192-208.
- L. D. Narins, A. Scott, A. Gautam, A. Kulkarni, M. Castanon, B. Kao, S. Ihorn, Y. T. Siu, J. M. Mason, A. M. Blum, I. Yoon, “Validated Image Caption Rating Dataset,” presented at the NeurlIPS, Neural Informations Processing Systems Datasets and Benchmarks Track, 2023.
- Andrew Taylor Scott, Lothar D Narins, Anagha Kulkarni, Mar Castanon, Benjamin Kao, Shasta Ihorn, Yue-Ting Siu, and Ilmi Yoon. 2023. Improved Image Caption Rating – Datasets, Game, and Model. In Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems (CHI EA ’23). Association for Computing Machinery, New York, NY, USA, Article 172, 1–7.
Collaborate With Us
We welcome collaboration from researchers, developers, educators, designers, and advocates who share our vision for accessible digital media. Whether you’re interested in contributing to system design, conducting user studies, or integrating YouDescribe into your curriculum or platform, we’re excited to explore new possibilities together.
Contact
Have questions about our project, publications, or platform features? We’d love to hear from you. Feel free to reach out to us at i.yoon@northeastern.edu with any inquiries, ideas, or feedback.