According to a report from The Information, OpenAI is developing a new tool capable of creating music from both text and audio cues.
Sources indicate that this technology could be applied to enhance videos with music or to add guitar backing to a vocal recording. It remains uncertain when OpenAI intends to release this tool or if it will be offered independently rather than as a feature within ChatGPT or the Sora video application.
The Information also reports that OpenAI is collaborating with Juilliard School students to annotate musical scores, which will serve as training material.
Although OpenAI has previously introduced generative music models, those were released before ChatGPT. More recently, the company has concentrated on developing audio models for converting text to speech and vice versa. Other organizations working on generative music technology include Google and Suno.
TechCrunch has contacted OpenAI for a response.
