Nvidia suggests that music producers could use Fugatto to experiment with initial ideas for songs, testing out different styles, instruments or voices, or even applying audio effects.

Nvidia claims a new AI audio generator can make sounds never heard before Fugatto can generate and edit music, speech, or sounds based on a text prompt.

However, instead of gorging on text, Fugatto was fed a mountain of audio data. The final model has 2.5 billion parameters and was trained on an Nvidia DGX system with 32 H100 Hopper AI accelerators.

The United States’ plan to “re-industrialize” technology manufacturing is “exactly the right thing,” Jensen Huang, CEO of the world’s largest chipmaker, said Thursday.

In a blog post detailing Fugatto, Nvidia ’s Richard Kerris claimed it offered more dexterity than any other AI model and holds the potential to revolutionise music through brand new sounds.

AI can now generate or transform any mix of music and sounds thanks to Fugatto, a new model from Nvidia.

Learn about the capabilities of NVIDIA’s Fugatto, an AI audio generator that can combine free-form instructions to create complex soundscapes and transform audio in ways previously unimaginable.

But Nvidia was also quick to highlight that models like Fugatto are best seen as a new tool for audio artists rather than a replacement for their creative talents.

Silicon Valley chipmaker Nvidia on Wednesday became the first publicly traded company to surpass a $4 trillion market ...

NVIDIA has debuted a new experimental generative AI model, which it describes as "a Swiss Army knife for sound." The model called Foundational Generative Audio Transformer Opus 1, or Fugatto, can ...

Nvidia calls Fugatto, short for Foundational Generative Audio Transformer Opus 1, a "Swiss Army knife for sound" as it jumps into the AI music space.