OpenAI is developing a new generative music tool that creates music from text and audio prompts, according to a report from The Information. The tool could add background music to existing videos or provide guitar accompaniment to a vocal track, sources indicated.
Details on the launch timeline remain unclear, as does whether the tool will launch as a standalone product or integrate with OpenAI’s ChatGPT and video app Sora. One source revealed that OpenAI is collaborating with students from the Juilliard School to annotate musical scores for training data.
Although OpenAI has previously released generative music models, those efforts predate the launch of ChatGPT. In recent years, the company has prioritized audio models for text-to-speech and speech-to-text functionalities. Competitors in the generative music space include Google and Suno.
