OpenAI Orchestrates a New Era: Generative Music Tool in the Making
OpenAI, the global leader in artificial intelligence technology, is reportedly developing a new generative music tool capable of creating music based on written or audio prompts, according to The Information, a U.S.-based technology news outlet, as cited by TechCrunch.
The tool will allow users to add background music to videos or generate instrumental accompaniments such as guitar tracks to complement a vocal recording. However, it remains uncertain when the tool will be released or whether it will be integrated with ChatGPT or the Sora video application.
Sources indicate that OpenAI is collaborating with several students from the Juilliard School to analyze and annotate musical scores in preparation for training data.
OpenAI had previously experimented with music-generation models, though those efforts predated the release of ChatGPT. In recent months, the company has been focusing on text-to-speech and speech-to-text audio models. Meanwhile, Google and Suno are also developing similar generative music technologies.
