OpenAI Develops New AI Tool To Create Music From Text And Audio Prompts

OpenAI is working on a new generative music tool capable of creating music from both text and audio prompts. The technology could be used to add soundtracks to videos or even compose instrumental accompaniments, such as guitar backing for vocal recordings.

While details about the launch timeline remain unclear, it’s also uncertain whether the tool will debut as a standalone product or be integrated into existing platforms like ChatGPT or the Sora video model.

To develop and refine the system, OpenAI has partnered with students from the Juilliard School, who are assisting in annotating music scores to train the model.

OpenAI has previously explored generative music systems, though those efforts predated ChatGPT. In recent years, the company’s audio research has primarily focused on text-to-speech and speech-to-text advancements. Other players in the generative music space include Google and Suno, both of which are pushing the boundaries of AI-driven sound creation.