Summary
OpenAI is reportedly developing an exciting new tool that can generate music from text and audio prompts. This innovation could allow users to add music to videos or create guitar accompaniments for vocals, expanding creative possibilities. While details on the launch timeline and product availability remain unclear, OpenAI is collaborating with Juilliard students to enhance the tool’s training data.
What Is OpenAI Working On?
According to a report by The Information, OpenAI is creating a generative music tool that takes text and audio prompts to produce music. This approach leverages AI to compose music tailored to specific inputs, potentially transforming how creators add soundtracks and accompaniments.
Potential Uses of the Tool
Sources suggest that this tool could be used to add music to existing videos or provide guitar accompaniment for vocal tracks. Such functionality would be valuable for content creators, musicians, and video editors looking to enhance their projects with custom-generated music.
Collaboration with Juilliard Students
OpenAI is reportedly working with students from the Juilliard School to annotate musical scores. This collaboration aims to provide high-quality training data to improve the AI’s understanding and generation of music.
OpenAI’s History with Generative Music
While OpenAI has released generative music models before, these efforts predate the launch of ChatGPT. More recently, the company has focused on audio models related to text-to-speech and speech-to-text technologies.
Other Companies in the Space
Other organizations, such as Google and Suno, are also developing generative music models, indicating growing interest and innovation in AI-generated music.
TechCrunch has reached out to OpenAI for comment on this development.