OpenAI is reportedly developing an artificial intelligence (AI) music tool that can generate music using text and audio prompts.
The prime motive behind this generative feature is to create original music from the dynamic combination of music text and audio prompts, and it’s envisioned to serve as a tool for generating instrumental backing for videos.
Following the discovery of new tool, The Juilliard School in the United States denied the reports that they came up with a music generation tool and confirmed that they had reached out to OpenAI but did not receive an immediate reply.
In 2019, a few years back before the explosive launch of ChatGPT, the company launched MuseNet, a “neutral network” that could create 4-minute compositions with 10 distinct instruments.
The announcement from OpenAI comes as other tech companies are inaugurating their own music tool.
Spotify has already launched a new feature that enhances user control and interactivity, and which can handle requests combining genre, mood and activity when voice commands are impractical.
Nevertheless, the integration of generative AI music tools that responds to both audio and text prompts marks a significant entry into a competitive market.
