OpenAI is reportedly developing a new tool that can create music from text and audio prompts, according to The Information.
Imagine typing out a short idea—or uploading a voice clip—and getting a full soundtrack in return. That’s the kind of tool OpenAI seems to be building. Sources say it could add background music to videos or even layer guitar accompaniment onto a vocal track. Pretty cool, right? Still, there’s no word yet on when it’ll launch or whether it’ll be part of ChatGPT, OpenAI’s video app Sora, or a standalone product.
Interestingly, OpenAI is said to be collaborating with students from the Juilliard School to help annotate musical scores. Those annotations could serve as valuable training data for the system—essentially teaching it how to “understand” music better.
OpenAI has experimented with generative music before, but those early efforts came before ChatGPT’s debut. Lately, the company’s focus has leaned more toward audio tools for text-to-speech and speech-to-text.
Of course, OpenAI isn’t the only player in this space. Google and Suno are also building generative music models of their own.
