NVIDIA’s Fugatto AI model can produce unique sounds based on text commands.
Technology giant NVIDIA, Fugatto developed a new artificial intelligence voice synthesis model called. This model allows users to create music, speech, or previously unheard sounds using text commands. Fugatto works by blending existing sound samples or creating brand new sounds from scratch.
Fugatto: Meowing Trumpets and Barking Saxophones
Fugatto can create unique sound combinations that challenge users’ imagination. For example, interesting instruments can be created, such as a trumpet that makes a meowing sound or a saxophone that makes a barking sound. It is also possible to change the vocals or instruments in the songs and adjust the tone and accent of the voice.
When developing Fugatto, NVIDIA researchers trained the model using a dataset of millions of audio samples. Thus, Fugatto can produce more accurate and diverse sounds. Researchers implemented various strategies to improve the model’s performance and add new capabilities.
Fugatto is not currently available to the public and it is unclear when it will be available. However, the video released by NVIDIA showcases Fugatto’s impressive capabilities. In the future, major advances can be made in the field of voice synthesis through the ethical use of artificial intelligence.
Fugatto opens a new era in sound synthesis technology, offering unlimited creative possibilities to musicians, sound designers and content creators. Let’s see how NVIDIA’s new AI model will shape the music world.