Saverio Cantoni

Nearly 20% of the world’s population is d/Deaf or Hard of Hearing. Speech-to-text functions are built into almost every pocket-sized device, automatic live captions are increasingly accurate, and auto-generated subtitles have become a content producer’s signature on social media. Yet no services describe live sound or music. This session will explore Spell, a tool that is aiming to close this gap by generating real-time closed captions and visualisations of live audio. Spell is a tool for normalising inclusion and access needs, which uses an AI supported prompter to make visual sound a possibility on every stage: for lyrics, speech, live captions, sign language prompts, and visual translations of incoming sound streams. The session will demonstrate how Spell, which not only captions language but also describes and translates any incoming live sound stream, will challenge audism in the music industry.