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 could possibly be used so as to add music to present movies, or so as to add guitar accompaniment to an present vocal observe, sources mentioned. It’s not clear when OpenAI plans to launch such a device or whether or not it could be out there as a standalone product (versus integrating with OpenAI’s ChatGPT and video app Sora).
One supply informed The Data that OpenAI is working with some college students from the Juilliard College to annotate scores as a approach to supply coaching knowledge.
Whereas OpenAI has launched generative music fashions up to now, they predate the launch of ChatGPT; extra not too long ago, the corporate has been growing audio fashions targeted 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.
