Can AI Compose Your Next Hit Song?

In partnership with

Start learning AI in 2025

Everyone talks about AI, but no one has the time to learn it. So, we found the easiest way to learn AI in as little time as possible: The Rundown AI.

It's a free AI newsletter that keeps you up-to-date on the latest AI news, and teaches you how to apply it in just 5 minutes a day.

Plus, complete the quiz after signing up and they’ll recommend the best AI tools, guides, and courses – tailored to your needs.

Sign up to start learning.

Nvidia has just unveiled Fugatto—a revolutionary AI model that promises to transform how we think about sound and audio creation. Whether you're a music producer, a game developer, or a creative director in advertising, this tool could completely change the game.

Fugatto—short for Foundational Generative Audio Transformer Opus—takes AI-powered audio generation to a whole new level. It seamlessly combines text prompts and audio files to create, transform, and enhance music, voices, and sounds in ways we've only imagined.

What Makes Fugatto Stand Out?

While many existing AI models can either compose music or manipulate audio in isolated ways, Fugatto offers unmatched versatility and creativity:

• Music Production: Generate music snippets based on a simple text prompt like “create an upbeat electronic tune with a tropical vibe” or “add a piano solo to this orchestral piece.” Producers can now experiment with instruments, styles, and effects faster than ever.

• Voice Customization: Adjust the accent, tone, or emotion in a voiceover, transforming a neutral script into an emotionally charged performance.

• Sound Design: Produce completely unique sounds—ones that have never been heard before—perfect for innovative soundscapes in music, games, or media.

• Audio Editing: Remove or add instruments to an existing track with precision, creating endless possibilities for remixing or enhancing old compositions.

The Technology Behind Fugatto

Fugatto’s power comes from its diverse team of creators hailing from India, Brazil, China, Jordan, South Korea, and beyond. This global collaboration has equipped the model with multi-accent and multilingual capabilities, making it a flexible tool for users around the world.

According to Rafael Valle, Nvidia’s manager of applied audio research, the team’s goal was ambitious: “We wanted to create a model that understands and generates sound like humans do.” Fugatto doesn’t just mimic—it understands the context and intention behind sounds, opening up new dimensions of creative possibilities.

Who Will Benefit from Fugatto?

1. Music Producers:

   • Rapidly prototype songs or soundscapes.

   • Experiment with genres, instruments, and effects.

   • Enhance overall sound quality with minimal effort.

2. Game Developers:

   • Modify sound effects dynamically to reflect gameplay changes.

   • Design immersive audio environments with ease.

   • Tailor pre-recorded assets for evolving in-game narratives.

3. Advertisers and Marketers:

   • Adapt campaigns for different regions by altering voice accents, languages, and emotional tones.

   • Customize voiceovers to connect with diverse audiences in a culturally resonant way.

   • Save time and resources with AI-driven precision edits.

Why Does This Matter?

The introduction of Fugatto signifies a major leap in the democratization of audio innovation. With this model, creative professionals no longer need to rely on extensive technical skills or expensive equipment to produce high-quality audio. The flexibility it provides will save time, reduce costs, and enable creatives to focus on what truly matters: their vision.

From music studios to gaming consoles, from advertising agencies to independent creators, Fugatto is poised to become a cornerstone of how audio is conceptualized and produced. Nvidia’s innovation doesn’t just offer tools—it opens doors to new ways of storytelling and expression.

What’s Next?

As Fugatto continues to evolve, its potential applications could expand even further. Think about real-time voice modulation during live events, personalized audio experiences for virtual reality, or even AI-generated film scores tailored to specific audiences.

With Fugatto, the future of sound is here. And the best part? It’s just getting started.