OpenAI is working on a brand new software that will generate music primarily based on textual content and audio prompts, in accordance to a report in The Information.
Such a software could possibly be used to add music to present movies, or to add guitar accompaniment to an present vocal monitor, sources mentioned. It’s not clear when OpenAI plans to launch such a software or whether or not it might be accessible as a standalone product (as opposed to integrating with OpenAI’s ChatGPT and video app Sora).
One supply instructed The Data that OpenAI is working with some college students from the Juilliard Faculty to annotate scores as a method to present coaching knowledge.
Whereas OpenAI has launched generative music fashions in the previous, they predate the launch of ChatGPT; extra not too long ago, the firm has been developing audio models targeted on text-to-speech and speech-to-text. Different corporations with generative music fashions embrace Google and Suno.
TechCrunch has reached out to OpenAI for remark.
Disclaimer: This article is sourced from external platforms. OverBeta has not independently verified the information. Readers are advised to verify details before relying on them.
