OpenAI has announced the development of a new tool that will allow users to generate music based on text and audio prompts.
According to The Information, this technology could be applied to add musical accompaniment to video content or to create guitar parts that complement pre-recorded vocal tracks. Currently, there is no information on the release date of the tool or whether it will be available as a standalone product, or integrated into ChatGPT or the Sora app.
Sources indicate that OpenAI is collaborating with students from the Juilliard School, who are aiding in annotating musical scores for training the model.
Previously, the company launched music generation models, but they were released before ChatGPT. It is known that OpenAI is currently focusing on audio models, particularly for converting text to speech and vice versa.
