OpenAI is developing a new music generation tool
What's the story
OpenAI is developing a new tool that would create music from text and audio prompts, according to The Information. The innovative tool can be used for various purposes, such as adding background scores to existing videos or providing guitar accompaniment for a vocal track. However, the exact launch date of the tool or whether it would be available as a standalone product remains unclear at this point.
Collaboration details
Collaborating with Juilliard School students
To develop this new tool, OpenAI is working with some students from the prestigious Juilliard School. The collaboration involves annotating musical scores to provide training data for the generative music model. This isn't the first time OpenAI has worked on generative music models, but it is a continuation of their efforts in this space.
Model development
Other companies have also ventured into generative music
OpenAI had launched generative music models before the launch of ChatGPT. However, their recent work has been on audio models for text-to-speech and speech-to-text conversions. These developments show how the company is constantly evolving its technology to include more complex tasks like music generation from simple prompts. Other tech giants like Google and Suno have also developed generative music models.