AI Content Describer

AI Content Describer is an add-on for the NVDA screen reader that uses multimodal AI models to generate descriptions of on-screen visual content — images, controls, icons, charts, and arbitrary screen regions — on demand. It gives NVDA users a JAWS-Picture-Smart-equivalent capability and is commonly used as a secondary verification tool when working with generative AI outputs that include visual elements (such as spreadsheet charts or conditionally formatted cells). Like other multimodal description tools, it operates on screenshots, can hallucinate details, and is subject to the limitations of whatever underlying model it calls.