Researchers have claimed to have created an AI audio generator that can create sounds that have never been heard before.
A new generative artificial intelligence model called Fugato has been created by a team at computer chipmaker Nvidia.
The tool allows users to edit or create audio using simple text prompts, such as removing a specific instrument from a song or changing someone’s voice.
In a detailed blog post about Fugato, Nvidia’s Richard Carus claimed that the tool provides more convenience than any other AI model and has the potential to change the world of music with new sounds.
Richard Carus further wrote that Fugato can be used to make a trumpet bark or a saxophone meow. Whatever users write, the model can create.
