OpenAI is developing an artificial intelligence tool that can generate music from text and audio prompts, signaling a new expansion into the fast-growing AI music industry, according to The Information.
The upcoming model would let users add custom music to videos or create instrument tracks — such as guitar accompaniments for vocals — offering powerful tools for musicians, filmmakers, and content creators. While OpenAI has not confirmed a release date, insiders say the product could be integrated into ChatGPT or Sora, the company’s AI video generator.
To ensure quality and artistic depth, OpenAI has reportedly partnered with students from the Juilliard School, who are annotating scores to train the model using expert-level compositions. The collaboration reflects OpenAI’s broader goal of blending human artistry with machine learning to enhance creativity rather than replace it.
The move puts OpenAI in direct competition with startups like Suno and tech giants like Google, both of which have already developed AI music tools capable of producing songs and instrumentals from short prompts.
This development marks OpenAI’s return to generative audio, a field it explored before launching ChatGPT, and underscores the company’s push to dominate every layer of the creative AI ecosystem — from writing and video to voice and now, music.
