OpenAI’s is Building an AI Tool That Turns Text Into Music

Every great move forward in your life begins with a leap of faith, a step into the unknown

OpenAI’s is Building an AI Tool That Turns Text Into Music

OpenAI is reportedly working on a new tool that can generate music from text and audio prompts, according to a report from The Information. The tool could be used for practical applications like adding music to existing videos or layering guitar accompaniment onto vocal tracks.

It’s still unclear when OpenAI plans to launch this new music generation capability or how it will be made available to users. The company might release it as a standalone product, or it could integrate the technology into existing platforms like ChatGPT or its video app Sora, which recently got updated with new social features.

To build out the training data for this tool, OpenAI is reportedly working with students from the Juilliard School to annotate musical scores. This isn’t OpenAI’s first venture into generative music, but their previous music models came out before ChatGPT launched. More recently, the company has focused its audio development efforts on text-to-speech and speech-to-text capabilities.

OpenAI would be entering a space where a few other players are already active. Google has its own generative music models, and Suno has gained attention as a dedicated music generation platform.