According to a report by The Information, OpenAI is developing a new instrument capable of creating music from text and audio cues.
Insiders claim that the tool could potentially be utilized for incorporating music into videos or providing guitar backing for a vocal track. It remains uncertain when OpenAI intends to release the tool or if it will be offered as a separate product, rather than being incorporated into OpenAI’s ChatGPT and Sora video application.
According to a source cited by The Information, OpenAI is collaborating with students from the Juilliard School to annotate musical scores for training purposes.
While OpenAI has previously introduced generative music models, these were launched before ChatGPT. More recently, the company has concentrated on creating audio models for converting text to speech and vice versa. Google and Suno are among the other companies that offer generative music models.
TechCrunch has contacted OpenAI for their input.
