OpenAI is developing a generative music tool that produces music from text and audio prompts, as reported by The Information. The tool aims to enable applications such as adding music to existing videos or providing guitar accompaniment to vocal tracks, according to sources cited in the report.
Sources indicate that the exact launch timeline for this tool remains unspecified. It is also unclear whether OpenAI intends to release it as a standalone product or integrate it into existing platforms like the ChatGPT chatbot and the Sora video generation application.
To support development, OpenAI is collaborating with students from the Juilliard School. One source informed The Information that these students are annotating musical scores to generate training data for the model. This effort builds on OpenAI’s prior experience with generative music, as the company released such models before the debut of ChatGPT in late 2022.
In recent years, OpenAI has shifted focus toward other audio technologies, including models for converting text to speech and speech to text. These advancements complement the broader landscape of generative audio tools, where companies like Google and Suno have also developed similar music generation models.
