OpenAI develops music production artificial intelligence

Some reports suggest that OpenAI plans to develop a generative artificial intelligence to produce music with text commands.

According to The Information, OpenAI is working on a new tool that can generate music for users based on text and audio input. According to sources, such a tool can be used to add music to existing videos or add guitar music to an audio track with a singer’s voice.

OpenAI is releasing a new tool for music production soon

The release date of this generative artificial intelligence by OpenAI has not yet been determined. It is also unclear whether the tool will be available as a standalone product or integrated with ChatGPT and the Sora video app.

To launch the service, OpenAI is working with a number of Juilliard School of Music students to annotate musical notes to provide training data for the model, a source familiar with the matter said.

OpenAI has released generative music models before, but these models were from the era before the introduction of ChatGPT, and in recent years the company has focused more on developing audio models for text-to-speech and speech-to-text conversion.

Last month, OpenAI released Sora, a standalone video production app that allows users to produce videos with artificial intelligence. In a short period of time, this application was able to achieve high popularity and reach the first rank of the App Store.

Google and Suno are also among the companies that have released music production models. Currently, there are various models available to users for producing music with artificial intelligence, although their quality may not be very favorable.

AI-generated music has also found its way onto platforms like Spotify, and even a band created entirely by AI managed to reach a record of one million streams on the platform.