Imagine a world where language is no longer a barrier to enjoying movies and TV shows. For people who are blind or visually impaired, audio description (AD) is a lifeline, painting vivid pictures with words. But what happens when the AD isn't available in your language? Researchers at the University of Zurich are tackling this challenge head-on with SwissADT, a groundbreaking AI system designed to translate audio descriptions for Swiss languages, opening up a world of entertainment to a wider audience. Switzerland, with its diverse linguistic landscape, presents a unique challenge. Creating AD in multiple languages is a costly and time-consuming process. SwissADT aims to automate this by leveraging the power of large language models (LLMs), like those behind ChatGPT, to translate AD scripts from English into German, French, and Italian. But it's not just about translating words; it's about capturing the essence of the visual experience. The team realized that simply translating text often misses crucial nuances. Their innovation? Incorporating video clips into the translation process. By feeding the AI both the text and key frames from the video, SwissADT gains a deeper understanding of the scene, leading to more accurate and engaging audio descriptions. Initial results are promising, showing that adding visual context significantly improves the quality of the translated AD. Human evaluations by AD professionals confirm that the AI-generated descriptions are not only fluent but also capture the important details, enhancing the viewing experience. This innovative approach has the potential to revolutionize accessibility services, not only in Switzerland but globally. While challenges remain, such as expanding language support and further refining the system's accuracy, SwissADT marks a significant step towards a more inclusive media landscape. The team's vision is to seamlessly integrate human expertise with AI's generative power, creating a future where everyone can enjoy the stories unfolding on screen, regardless of language or visual ability.