Adds audio descriptions to videos instantly to make them accessible
What it does
According to Google, there are over 14 billion publicly viewable videos on YouTube; yet only a small fraction of them can be accessed by people with visual impairments. According to the WHO, at least 2.2 billion people worldwide suffer from a near or distance vision impairment, preventing them from fully experiencing the vast repository of video content on the world’s leading video platforms.
Audio description is a longstanding practice in TV and film, and considered a solution to allow the blind and visually impaired community to consume and enjoy video based content... But the process of audio describing videos is time and cost-prohibitive, preventing audio descriptions from reaching the masses via independently created web-based videos.
Enter ViddyScribe: a web platform where video creators can upload their videos and quickly receive them back fully audio-described, so that the videos can be shared with and enjoyed by the blind community.
The Gemini API is used to analyze the user’s uploaded video and generate contextually-aware timestamped audio descriptions for every meaningful section of the video. Then, the audio descriptions are converted into speech and placed at the timestamps, while we insert freeze frames, smooth audio transitions, and generated background audio to aid in creating a pleasant listening experience.
Created by two volunteers for the blind with backgrounds in videography and impactful solutions, ViddyScribe aims to make all videos truly inclusive.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],[],[],[],null,["# ViddyScribe\n\n[See all winners](/competition#w-8) \nBest Web app \n\nViddyScribe\n===========\n\nAdds audio descriptions to videos instantly to make them accessible \nWhat it does\n\nAccording to Google, there are over 14 billion publicly viewable videos on YouTube; yet only a small fraction of them can be accessed by people with visual impairments. According to the WHO, at least 2.2 billion people worldwide suffer from a near or distance vision impairment, preventing them from fully experiencing the vast repository of video content on the world's leading video platforms. \n\nAudio description is a longstanding practice in TV and film, and considered a solution to allow the blind and visually impaired community to consume and enjoy video based content... But the process of audio describing videos is time and cost-prohibitive, preventing audio descriptions from reaching the masses via independently created web-based videos. \n\nEnter ViddyScribe: a web platform where video creators can upload their videos and quickly receive them back fully audio-described, so that the videos can be shared with and enjoyed by the blind community. \n\nThe Gemini API is used to analyze the user's uploaded video and generate contextually-aware timestamped audio descriptions for every meaningful section of the video. Then, the audio descriptions are converted into speech and placed at the timestamps, while we insert freeze frames, smooth audio transitions, and generated background audio to aid in creating a pleasant listening experience. \n\nCreated by two volunteers for the blind with backgrounds in videography and impactful solutions, ViddyScribe aims to make all videos truly inclusive. \nBuilt with\n\n- Web/Chrome \nTeam \nBy\n\nThe Accessibros \nFrom\n\nUnited States \nMore winners \n[Prospera\nMost Useful app / Best Flutter app](/competition/projects/prospera) [Trippy\nBest use of Firebase app](/competition/projects/trippy) \n[](/competition)"]]
