OpenAI is working on a new tool that will generate music based on text and audio prompts, according to the OpenAI website. Report on information.
Such a tool could be used to add music to existing videos, or to add guitar accompaniment to an existing audio track, the sources said. It’s not clear when OpenAI plans to release such a tool or if it will be available as a standalone product (rather than integrating with ChatGPT and OpenAI’s ChatGPT). Sora video application).
One source told The Information that OpenAI is working with some students from the Juilliard School to transcribe results as a way to provide training data.
While OpenAI has released generative music models in the past, it predated the launch of ChatGPT; Recently, the company Developing acoustic models Focus on text-to-speech and speech-to-text conversion. Other companies with generative music models include Google and Suno.
TechCrunch has reached out to OpenAI for comment.