OpenAI is working on a new tool that will generate music based on text and audio prompts A report by The Information.
Such a tool can be used to add music to an existing video or add guitar accompaniment to an existing vocal track, sources said. It’s unclear when OpenAI plans to launch such a tool or if it will be available as a standalone product (as opposed to integrating OpenAI’s ChatGPT and video app with Sora).
A source told The Information that OpenAI is working with some students at the Juilliard School to annotate the scores as a way to provide training data.
Although OpenAI has launched generative music models in the past, they predated the launch of ChatGPT; More recently, the company has been Developing audio models Focused on text-to-speech and speech-to-text. Other companies with generative music models include Google and Suno.
TechCrunch has reached out to OpenAI for comment.