NvidiaA blog post was published on November 25th announcing the push of theOut Music Generation AI Models FugattoIt is claimed to be "the world's most flexible sound machine", with fine control over sound generation.
NVIDIA says the tool is like the "Swiss Army Knife" of sound, with the ability to not only create music and modify sounds, but also the flexibility to mix music, vocals and sound effects, and even create unprecedented sounds.
Users simply type in a text description or insert some audio, and Fugatto generates corresponding music clips, sound effects, and even changes the accent and emotion of the human voice based on the description.
For example, users can type in "a meowing trumpet" or "create a tune that includes saxophone howls, dog barks, and electronica," and create music based on the user's whimsical cues.
Fugatto can also generate unique sound effects, such as "deep bass pulses intertwined with high pitched digital chirps, like the sound of a giant intelligent machine waking up".
Fugatto can also change the audio clips entered by the user, adjusting the accent and tone of the voice, e.g. turning a soft whisper into an angry growl and so on.
For musical artists, Fugatto can also separate the lead vocals in a song, add instruments, and even replace piano sounds with operatic singing, adapting musical melodies at will.