OpenAI has announced plans to develop a cutting-edge tool that can generate music based on text and audio cues, as reported by The Information.
The innovative tool in the works at OpenAI aims to create music tailored to specific prompts, such as text and audio inputs. This technology could revolutionize the music industry by enabling the addition of custom soundtracks to videos or enhancing existing vocal tracks with guitar accompaniments. The exact release date and availability of the tool remain uncertain, as it’s unclear whether it will be a standalone product or integrated with OpenAI’s other applications like ChatGPT and Sora.
To enhance the tool’s capabilities, OpenAI is collaborating with students from the prestigious Juilliard School to annotate musical scores and gather valuable training data. While OpenAI has previously introduced generative music models, their focus has shifted towards developing advanced audio models, particularly in the realms of text-to-speech and speech-to-text technologies. Notably, other tech giants like Google and emerging startups like Suno are also exploring generative music models in the industry.
For further insights into this groundbreaking project, TechCrunch has reached out to OpenAI for additional comments and information.
