Sony Pixel Power calrec Sony

Now Hear This: World's Most Flexible Sound Machine Debuts

25/11/2024

A team of generative AI researchers created a Swiss Army knife for sound, one that allows users to control the audio output simply using text.

While some AI models can compose a song or modify a voice, none have the dexterity of the new offering.

Called Fugatto (short for Foundational Generative Audio Transformer Opus 1), it generates or transforms any mix of music, voices and sounds described with prompts using any combination of text and audio files.

For example, it can create a music snippet based on a text prompt, remove or add instruments from an existing song, change the accent or emotion in a voice - even let people produce sounds never heard before.

This thing is wild, said Ido Zmishlany, a multi-platinum producer and songwriter - and cofounder of One Take Audio, a member of the NVIDIA Inception program for cutting-edge startups. Sound is my inspiration. It's what moves me to create music. The idea that I can create entirely new sounds on the fly in the studio is incredible.

A Sound Grasp of Audio We wanted to create a model that understands and generates sound like humans do, said Rafael Valle, a manager of applied audio research at NVIDIA and one of the dozen-plus people behind Fugatto, as well as an orchestral conductor and composer.

Supporting numerous audio generation and transformation tasks, Fugatto is the first foundational generative AI model that showcases emergent properties - capabilities that arise from the interaction of its various trained abilities - and the ability to combine free-form instructions.

Fugatto is our first step toward a future where unsupervised multitask learning in audio synthesis and transformation emerges from data and model scale, Valle said.

A Sample Playlist of Use Cases For example, music producers could use Fugatto to quickly prototype or edit an idea for a song, trying out different styles, voices and instruments. They could also add effects and enhance the overall audio quality of an existing track.

The history of music is also a history of technology. The electric guitar gave the world rock and roll. When the sampler showed up, hip-hop was born, said Zmishlany. With AI, we're writing the next chapter of music. We have a new instrument, a new tool for making music - and that's super exciting.

An ad agency could apply Fugatto to quickly target an existing campaign for multiple regions or situations, applying different accents and emotions to voiceovers.

Language learning tools could be personalized to use any voice a speaker chooses. Imagine an online course spoken in the voice of any family member or friend.

Video game developers could use the model to modify prerecorded assets in their title to fit the changing action as users play the game. Or, they could create new assets on the fly from text instructions and optional audio inputs.

Making a Joyful Noise One of the model's capabilities we're especially proud of is what we call the avocado chair, said Valle, referring to a novel visual created by a generative AI model for imaging.

For instance, Fugatto can make a trumpet bark or a saxophone meow. Whatever users can describe, the model can create.

With fine-tuning and small amounts of singing data, researchers found it could handle tasks it was not pretrained on, like generating a high-quality singing voice from a text prompt.

Users Get Artistic Controls Several capabilities add to Fugatto's novelty.

During inference, the model uses a technique called ComposableART to combine instructions that were only seen separately during training. For example, a combination of prompts could ask for text spoken with a sad feeling in a French accent.

The model's ability to interpolate between instructions gives users fine-grained control over text instructions, in this case the heaviness of the accent or the degree of sorrow.

I wanted to let users combine attributes in a subjective or artistic way, selecting how much emphasis they put on each one, said Rohan Badlani, an AI researcher who designed these aspects of the model.

In my tests, the results were often surprising and made me feel a little bit like an artist, even though I'm a computer scientist, said Badlani, who holds a master's degree in computer science with a focus on AI from Stanford.

The model also generates sounds that change over time, a feature he calls temporal interpolation. It can, for instance, create the sounds of a rainstorm moving through an area with crescendos of thunder that slowly fade into the distance. It also gives users fine-grained control over how the soundscape evolves.

Plus, unlike most models, which can only recreate the training data they've been exposed to, Fugatto allows users to create soundscapes it's never seen before, such as a thunderstorm easing into a dawn with the sound of birds singing.

A Look Under the Hood Fugatto is a foundational generative transformer model that builds on the team's prior work in areas such as speech modeling, audio vocoding and audio understanding.

The full version uses 2.5 billion parameters and was trained on a bank of NVIDIA DGX systems packing 32 NVIDIA H100 Tensor Core GPUs.

Fugatto was made by a diverse group of people from around the world, including India, Brazil, China, Jordan and South Korea. Their collaboration made Fugatto's multi-accent and multilingual capabilities stronger.

One of the hardest parts of the effort was generating a blended dataset that contains millions of audio samples used for training. The team employed a multifaceted strategy to generate data and instructions that considerably expanded the range of tasks the model could perform, while achieving more accurate performance and enabling new tasks without requiring additional data.

They also scrutinized existing datasets to reveal new relationships among the dat
LINK: https://blogs.nvidia.com/blog/fugatto-gen-ai-sound-model/...
See more stories from nvidia

Most recent headlines

05/01/2027

Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be demoed at CES 2026

Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be ...

07/10/2026

Dalet Flex LTS Delivers Smarter Media Operations from Ingest to Distribution

Dalet, a leading technology and service provider for media-rich organizations, today announced the latest Long-Term Supported (LTS) release of Dalet Flex. Build...

06/09/2026

Dolby and MagentaTV Bring Fans Closer to the FIFA World Cup 2026 in Germany with Dolby Vision and Dolby Atmos

June 9 2026, 23:00 (PDT) Dolby and MagentaTV Bring Fans Closer to the FIFA Worl...

13/08/2026

ASG Adds Eran Binyamin Zeitoun as Senior Technical Program Manager

Share Copy link Facebook X Linkedin Bluesky Email...

13/08/2026

Vinten To Feature Manual, Robotic Camera Support Offerings At IBC 2026

Share Copy link Facebook X Linkedin Bluesky Email...

13/08/2026

SMPTE Unveils IBC 2026 Plans

Share Copy link Facebook X Linkedin Bluesky Email...

13/08/2026

IP Showcase on the Water Announces Schedule for IBC 2026

Share Copy link Facebook X Linkedin Bluesky Email...

13/08/2026

Spectrum, Optimum Ink New Deals for News Carriage and Ads

Share Copy link Facebook X Linkedin Bluesky Email...

13/08/2026

IAB Tech Lab Updates Privacy Standards

Share Copy link Facebook X Linkedin Bluesky Email...

13/08/2026

Suitest Highlights New AI-Powered Device Testing and Qual...

Suitest's Test Automation Platform Simplifies Video Quality Assurance, Monitoring, and Device Certification Across the OTT Ecosystem At IBC2026, Suitest, a...

13/08/2026

Cinegy showcases powerful, agile, cost-effective media so...

Cinegy GmbH, the premier provider of software-defined television technology, will have its key software solutions ready to demonstrate at SET Expo 2026 (18 20...

13/08/2026

Scripps Research establishes endowed chair honoring Peter K. Vogt, influential pioneer in cancer research

Scripps Research has established the Peter K. Vogt Endowed Chair, a new faculty ...

13/08/2026

New research offers fresh insights for how to make better vaccines

LA JOLLA, CA-A vaccine's molecular structure plays a key role in determining how the immune system responds and prepares to protect the body from future exp...

12/08/2026

Op-Ed: The Versioning Playbook - How Rights Holders are Getting More From Live Events

Traditional live sports production has focused on creating the best possible pro...

12/08/2026

IBC 2026: FOR-A to Demonstrate Production and Processing Solutions

FOR-A will showcase a range of broadcast and production products at IBC2026 (Stand 2.B53, Amsterdam RAI, September 11-14), including software-based switching, A...

12/08/2026

IBC 2026: AMWA and EBU to Demo NMOS BCP-008 Multi-Vendor IP Status Reporting

The Advanced Media Workflow Association (AMWA) and EBU will host live demonstrations of NMOS BCP-008 Minimum Status Reporting at IBC2026 (September 11-14) on th...

12/08/2026

IBC 2026: Dalet Launches Solution Suites for Media Production and Archive Management

Dalet has announced Dalet Solution Suites, a portfolio of cloud-native solutions...

12/08/2026

Net Insight Enables Centralized Remote Production of Blinkfestivalen 2026 for NRK

Net Insight has announced that DMC Production Norway has selected its Open Live ...

12/08/2026

Zixi Appoints Alyson Stewart as Senior Director of Sales

Zixi has appointed Alyson Stewart as Senior Director of Sales. Stewart will be responsible for direct sales and partnerships, with a focus on broadcasters, medi...

12/08/2026

LiveU Powers Host Broadcast Operations at 2026 Glasgow Games

LiveU's LU900Q intelligent production unit was deployed as part of the host broadcast operation for the Games in Glasgow (July 23-August 2, 2026). Host broa...

12/08/2026

Disney+ and ESPN Acquire Multi-Year Formula E Rights Beginning 2026/27 Season

Disney , ESPN, and Formula E have announced a multi-year deal bringing all Formula E races to Disney and ESPN in the U.S. and to Disney in most international...

12/08/2026

PSSI Launches X-LIVE Managed Service for Live Event Transmission

PSSI has launched X-LIVE, a managed service offering dedicated engineering resources and Appear encoding infrastructure for live event signal processing and tra...

12/08/2026

MoonPay X Games League Draws 18.3 Million Viewers in Inaugural Summer Season

The inaugural MoonPay X Games League Summer Season reached 18.3 million unique live viewers across three stops on ABC and ESPN, a 78.5% increase compared to the...

12/08/2026

IBC 2026: BBright Adds RIST Support to IP-Gateway

BBright will showcase an expanded IP-Gateway at IBC2026, adding support for all RIST profiles to its existing support for MPEG Transport Stream over IP with SMP...

12/08/2026

IBC 2026: BBright Adds EBU OGraf Graphics Support to UHD and ST 2110 Playout Platform

BBright will demonstrate EBU OGraf animated graphics support in its software-bas...

12/08/2026

Interra Systems to Showcase QC and Monitoring Solutions at SET Expo 2026

Interra Systems will demonstrate its ORION, BATON, BATON Captions, and VEGA solutions at SET Expo 2026 (August 17-20, Distrito Anhembi, S o Paulo) at partner Li...

12/08/2026

DPA Microphones Appoints Raul Contreras as West Coast Regional Sales Manager

DPA Microphones has appointed Raul Contreras as West Coast Regional Sales Manager. In the role, Contreras will oversee sales and customer relationships througho...

12/08/2026

Save the Date: SVG LIVE! Returns to LA Nov. 10 to Spotlight Sports & Entertainment Production

Live spectacles ranging from the Super Bowl and FIFA World Cup to the Oscars and...

12/08/2026

Love, Separation, and the Cost of Comfort in How to Divorce During the War

Writer-Director Andrius Bla evi ius and crew attend the premiere of How to Divorce During the War at The Ray Theatre on January 26, 2026, in Park City, UT. (P...

12/08/2026

SSL 360 gets a major update

Enhanced DAW & plug-in control for the UC1, UF8 and UF1 The software that powers SSL's range of control surfaces has just received a major update that d...

12/08/2026

Triton Audio launch the Tilt EQ

In-line preamp features one-knob EQ In addition to their range of in-line preamps, Triton Audio recently managed to squeeze a compressor into an enclosure t...

12/08/2026

AudioRoute from Arvital Audio

Captures system audio with or without a DAW Depending on your setup, capturing system audio in a DAW can be a tedious process, so much so that Arvital Audio...

12/08/2026

2026 NATIONAL NAIDOC AWARDS TO BROADCAST ON NITV LIVE AND DIRECT FROM MPARNTWE

2026 NATIONAL NAIDOC AWARDS TO BROADCAST ON NITV LIVE AND DIRECT FROM MPARNTWE 12 August, 2026 Media releases First Nations excellence will be celebrated l...

12/08/2026

More than six million sports fans stay with SBS for Tour de France and Tour de France Femmes Avec Zwift

More than six million sports fans stay with SBS for Tour de France and Tour de F...

12/08/2026

Nielsen Introduces Groundbreaking Streaming Ad Measurement in Brazil

Nielsen is cementing Digital Ad Intel as the new go-to currency for digital ad intelligence in Brazil-now with streaming monitoring in the mix. S o Paulo, Augu...

12/08/2026

LPTV Advocates Petition FCC for Voluntary 5G Broadcasts

Share Copy link Facebook X Linkedin Bluesky Email...

12/08/2026

Tubi Media Group Inks Content Discovery Deal with Gracenote

Share Copy link Facebook X Linkedin Bluesky Email...

12/08/2026

Matrox Video Showcases IP-Based and Software-Defined Tech...

As Matrox Video celebrates 50 years of trusted innovation, the company will showcase its portfolio of interoperable IP technologies and software-defined innovat...

12/08/2026

SMPTE Showcases AI and Open Media Workflows and Industry...

SMPTE, the home of media professionals, technologists and engineers, today announced a program of expert-led sessions, professional workshops and networking eve...

12/08/2026

Berklee Announces Full Details for Inaugural Block Party, a Music Festival Next to Fenway Park

Berklee Announces Full Details for Inaugural Block Party, a Music Festival Next ...

12/08/2026

ACLU Requests ABC Station Probe Documents from FCC

Share Copy link Facebook X Linkedin Bluesky Email...

12/08/2026

Roger Keating To Retire from Hearst Television

Share Copy link Facebook X Linkedin Bluesky Email...

12/08/2026

Netflix Closes U.S. Upfronts, Nearly Doubles Ad Commitments

Share Copy link Facebook X Linkedin Bluesky Email...

12/08/2026

CBS Pittsburgh Debuts New AR/VR News Studio

Share Copy link Facebook X Linkedin Bluesky Email...

12/08/2026

Matthews Intros T-Go Extreme Rigging Solutions

Matthews Studio Equipment introduces T-Go Mounting Solutions extreme camera rigging systems, engineered for the most demanding environments in motion picture pr...

12/08/2026

Anton Bauers EDEN Becomes Only Mobile Power Station in it...

Anton/Bauer, a Videndum brand and the industry leader in mobile power solutions for broadcast and cinematic production, announces that the EDEN Mobile Power Sta...

12/08/2026

TAG Video Systems Cuts Hardware Costs for Customers with...

TAG Video Systems, the global leader in software-based IP monitoring and multiviewer solutions, today announced a memory usage optimization that lowers the tota...

12/08/2026

Unified Streaming Launches Trusted Media - C2PA in Dynami...

Unified Streaming announces Trusted Media, a new solution that enables broadcasters, streaming platforms, and premium content owners to attach verifiable authen...

12/08/2026

Tedial Powers the AI-Driven Media Supply Chain at IBC 202...

Combining intelligent automation, composable business services and user-centric experiences The media industry is entering a new phase where AI intelligence is...

12/08/2026

DPA Microphones Appoints Raul Contreras as West Coast Reg...

DPA Microphones welcomes Raul Contreras as its new West Coast Regional Sales Manager. In this role, Contreras will oversee sales and customer relationships thro...