OpenAI is developing a new generative music tool capable of creating music from text and audio prompts, according to a report by The Information. The tool could enable users to enhance videos with custom soundtracks or add instrumental accompaniments—such as guitar—onto existing vocal recordings. Details about the tool’s release timeline remain unclear, and it’s uncertain whether it will launch as a standalone product or be integrated into existing OpenAI platforms like ChatGPT or the video generation app Sora. One source revealed that OpenAI is collaborating with students from the Juilliard School to annotate musical scores, helping build high-quality training data for the model. This effort underscores the company’s focus on refining the precision and artistic quality of its generative audio outputs. Although OpenAI previously released generative music models before the rise of ChatGPT, its recent focus has shifted toward advancing audio technologies centered on text-to-speech and speech-to-text capabilities. Meanwhile, other tech companies such as Google and Suno have already launched their own generative music tools. OpenAI has not yet commented on the new project. TechCrunch has reached out for confirmation and additional details.