OpenAI reportedly developing new generative music tool

OpenAI is currently developing a groundbreaking tool designed to create music from both text and audio prompts, as revealed in a report by The Information. This innovative technology aims to enhance video content by seamlessly integrating music or even providing guitar accompaniments for vocal tracks. While details about the launch timeline remain vague, there is speculation about whether this tool will function independently or be integrated into OpenAI's existing platforms like ChatGPT and the video application Sora. Sources indicate that OpenAI is collaborating with students from the prestigious Juilliard School to gather annotations for musical scores, which will serve as vital training data for the tool's development. Although OpenAI has previously introduced generative music models prior to the ChatGPT era, recent efforts have shifted towards audio models concentrating on text-to-speech and speech-to-text technologies. Notably, competitors such as Google and Suno have also ventured into the realm of generative music modeling. TechCrunch has reached out to OpenAI for further insights regarding this exciting development.