OpenAI is reportedly working on a generative music tool that can produce music from text and audio prompts, according to a report by The Information. The tool could enable users to add music to existing videos or create guitar accompaniment for vocal tracks.
Details on when the tool might launch or whether it will be offered as a standalone product remain unclear. It could potentially integrate with OpenAI’s existing platforms, including ChatGPT and the video app Sora.
Sources told The Information that OpenAI is collaborating with students from the Juilliard School to annotate musical scores, helping to create training data for the AI models.
While OpenAI has previously released generative music models, these predate the launch of ChatGPT. More recent developments have focused on audio models for text-to-speech and speech-to-text applications.
The move comes as other tech companies, including Google and Suno, continue to explore generative music capabilities, reflecting growing interest in AI-assisted music creation.
