OpenAI Developing New Tool to Generate Music from Text and Audio Prompts
OpenAI is reportedly in the process of creating a revolutionary tool that will utilize text and audio prompts to generate music, as detailed in a recent report by The Information.
This innovative tool has the potential to enhance videos by adding customized music or even accompany vocal tracks with guitar melodies, according to insider sources. The exact release date of this tool remains uncertain, as does whether it will be offered as a standalone product or integrated into existing OpenAI platforms such as ChatGPT and Sora.
Collaboration with Juilliard School Students
One source revealed that OpenAI is collaborating with students from the prestigious Juilliard School to annotate musical scores, providing valuable training data for the project.
Evolution of OpenAI’s Music Models
While OpenAI has previously introduced generative music models, these were developed before the introduction of ChatGPT. In recent times, the company has shifted its focus to audio models specializing in text-to-speech and speech-to-text capabilities. Other industry players venturing into generative music models include Google and Suno.
Seeking Clarification from OpenAI
As JS seeks to delve further into this groundbreaking development, OpenAI has been contacted for additional comments and insights.