NVIDIA's new AI model Fugatto can create audio from text prompts

NVIDIA's Fugatto generates audio from text, offering versatile sound creation.

: NVIDIA's Fugatto is an AI model that creates audio from text prompts and modifies existing audio files. Developed by AI experts globally, it's praised for its multi-accent and multilingual proficiency. Music producers, language tools, and game developers could benefit from its versatile capabilities. No public access plans announced yet, but similar models by Meta and Google exist.

NVIDIA introduces Fugatto, an innovative generative AI model capable of producing audio from text prompts. The model also modifies existing music and sound files, showcasing its versatility. It's the result of a collaboration among AI researchers worldwide, which enhances its multi-accent and multilingual features.

Rafael Valle, a key researcher, compares Fugatto to a 'Swiss Army knife for sound,' highlighting its ability to understand and generate audio akin to human processes. The model could revolutionize music production, language learning, and video game development by providing easily editable audio prototypes and diversified language tools.

Despite the promising applications, NVIDIA has not disclosed details about public access to Fugatto. Similar technologies by Meta and Google, like MusicLM, offer comparable text-to-audio capabilities. These advancements suggest a growing trend in utilizing AI for creative audio solutions.

Generative AIAudio Creationtechnology