<ul><li>NVIDIA has announced a new text-to-audio model called Fugatto, which can create ‘any combination of music, videos and sounds’.</li><li>Fugatto is trained on 2.5 billion parameters and built on top of NVIDIA DGX systems, with 32 NVIDIA H100 GPUs.</li><li>The tool is positioned for audio producers, video game developers, language learning tools, and ad agencies.</li><li>When released, Fugatto will compete with existing audio generation tools such as ElevenLabs and SunoAI.</li></ul>

NVIDIA Strikes a Chord with Fugatto

Discover more