Reports indicate that OpenAI is developing a cutting-edge generative music tool capable of producing original compositions from both text and audio prompts.

According to The Information, the innovative system could soon enable users to add background music to videos or create instrumental accompaniments, such as guitar tracks for existing vocals.

Though the official launch date remains undisclosed, sources suggest that OpenAI may integrate the new music feature within its existing platforms—such as ChatGPT or the video-generation tool, Sora—rather than releasing it as a separate product.

Insiders also revealed that OpenAI has partnered with students from the prestigious Juilliard School to annotate musical scores, providing valuable training data to refine the AI’s musical understanding.

While OpenAI has previously explored generative music models, these early projects came before the debut of ChatGPT.

In recent years, the company has focused primarily on developing audio systems for text-to-speech and speech-to-text applications.

The move positions OpenAI alongside other tech giants like Google and Suno, who are also advancing in the field of AI-generated music.

Source: Techcrunch