OpenAI, a leading company in the field of artificial intelligence, is reportedly working on a new generative music tool. According to a report from a reliable technology source, this new tool will be able to generate music using text input or existing voice commands. This development demonstrates the company’s intention to expand its generative AI capabilities into a new area, following its successes in text with ChatGPT and video with Sora.
New Move from OpenAI: AI to Generate Music from Text is Coming
According to industry sources, this new tool could have a wide variety of uses. For example, users could use this technology to add background music to existing videos. Another potential use case is the ability to add accompaniment instruments like guitar to an existing vocal recording. These features could provide significant benefits, particularly for content creators and musicians.
However, it is not yet clear when the tool will be released or what its strategy will be. It is currently unknown whether this technology will be integrated into existing platforms like ChatGPT and the video creation tool Sora, or whether it will be offered as a standalone product. A source speaking to the international press stated that OpenAI is collaborating with students at the Juilliard School to collect training data. These students are reportedly studying musical scores to train the AI.
OpenAI had previously released generative music models before ChatGPT became popular. However, the company has recently focused more on audio technologies such as text-to-speech and voice-to-text conversion. Competitors like Google and Suno also have similar technologies in the music generation space. This new move by OpenAI appears to intensify competition in the market. While the tech press has reached out to OpenAI for comment, the company has not yet issued an official statement.
What are your thoughts on the advancements made in AI in music generation? Would you consider using such a tool? Share your thoughts with us in the comments section.
