Audible Sight is a computer vision application that uses AI to automatically generate audio descriptions for videos, ensuring compliance with Section 508, WCAG, and ADA standards. This technology enables content creators to make their videos accessible to blind and low-vision individuals, addressing the significant gap in accessible video content on the internet.
Funding
Funding not disclosed
Founders
Product
Problem
A significant portion of online video content lacks audio descriptions, making it inaccessible to blind and low-vision individuals. Traditional audio description methods are time-consuming and require specialized skills, creating a barrier for content creators seeking to comply with accessibility standards like Section 508, WCAG, and ADA.
Solution
Audible Sight is a computer vision application that automatically generates audio descriptions for videos, enabling content creators to make their content accessible. The platform uses AI to analyze video content, break it down into logical scenes, and generate corresponding text descriptions. These descriptions are then converted into lifelike synthetic speech and inserted into the video with small pauses between scenes, adhering to the extended audio description standard. The platform is designed for non-technical users, allowing them to easily edit descriptions and ensure compliance with accessibility standards.
Target Audience
The primary target audience includes content creators, educational institutions, government agencies, and organizations that need to make their video content accessible to individuals with visual impairments.
Features
- AI-powered video analysis for automatic scene detection and description generation
- Text-to-speech conversion using lifelike synthetic voices
- Extended audio description insertion with automated pauses
- User-friendly interface for editing and customizing descriptions
- Compliance with Section 508, WCAG, ADA, and EAA standards