OpenAI is working on a revolutionary tool that will enable music generation through text and audio prompts.
According to The Information, this new technology could be used to add musical backing to videos or to create guitar parts for pre-recorded vocal tracks. It is currently unclear when the tool will be unveiled or if it will be available as a standalone product like Suno, or integrated into ChatGPT or the Sora video application.
Sources indicate that OpenAI is collaborating with students from Juilliard School to assist in annotating musical scores for training materials.
Previously, the company launched music generation models, but these were released before ChatGPT. It is known that OpenAI is currently focused on audio models, particularly for converting text to speech and vice versa.