OpenAI is engaged on a brand new device that may generate music based mostly on textual content and audio prompts, in keeping with a report in The Data.
Such a device may very well be used so as to add music to current movies, or so as to add guitar accompaniment to an current vocal observe, sources stated. It’s not clear when OpenAI plans to launch such a device or whether or not it could be accessible as a standalone product (versus integrating with OpenAI’s ChatGPT and video app Sora).
One supply advised The Data that OpenAI is working with some college students from the Juilliard College to annotate scores as a approach to supply coaching information.
Whereas OpenAI has launched generative music fashions previously, they predate the launch of ChatGPT; extra just lately, the corporate has been growing audio fashions centered on text-to-speech and speech-to-text. Different corporations with generative music fashions embody Google and Suno.
TechCrunch has reached out to OpenAI for remark.