SAN FRANCISCO – OpenAI is reportedly working on a new artificial intelligence tool that can generate music from both text and audio prompts, according to a report by The Information.
The upcoming model could allow users to add music to videos or create instrument accompaniments, such as guitar tracks for vocals, expanding creative possibilities for musicians, content creators, and filmmakers.
Read More: OpenAI becomes world’s most valuable startup at $500B
Although no official release date has been confirmed, sources said it remains unclear whether the tool will be launched as a standalone platform or integrated into ChatGPT or Sora, OpenAI’s video-generation model.
To ensure high-quality training data, OpenAI has partnered with students from the Juilliard School, one of the world’s leading music conservatories. These students are annotating music scores to help the AI learn from expert-level compositions and performances.
The partnership reflects OpenAI’s broader mission to combine human artistry with machine learning, emphasizing that such innovations are designed to enhance human creativity rather than replace it.
Read More: WhatsApp’s New AI Feature Lets You Create Stunning Images Instantly
OpenAI previously explored generative music models before the launch of ChatGPT, but in recent years, the company has focused primarily on text-to-speech and speech-to-text technologies. With this new project, OpenAI appears to be re-entering the generative music space, competing with companies like Google and Suno, both of which already offer AI-powered music tools.