OpenAI reportedly developing new generative music tool

OpenAI is working on a new tool that would generate music based on text and audio prompts a report in De Informatie.

Such a tool could be used to add music to existing videos, or to add guitar accompaniment to an existing vocal track, sources said. It’s not clear when OpenAI plans to launch such a tool and whether it will be available as a standalone product (as opposed to integration with OpenAI’s ChatGPT and video app Sora).

One source told The Information that OpenAI is working with some students at the Juilliard School to annotate scores as a way to provide training data.

Although OpenAI has launched generative music models in the past, they predate the launch of ChatGPT; more recently the company has been develop audio models focused on text-to-speech and speech-to-text. Other companies with generative music models include Google and Suno.

TechCrunch has reached out to OpenAI for comment.