Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

Nvidia's new AI model Fugatto can generate music and audio

Nov 25, 2024 - fastcompany.com
Nvidia has unveiled a new artificial intelligence model, Fugatto, designed to generate and modify music and audio. The technology, aimed at music, film, and video game producers, can alter voices, generate new sounds, and create sound effects and music from text descriptions. Unlike other AI technologies, Fugatto can modify existing audio, such as transforming a piano line into a human voice or altering the accent and mood of a spoken word recording. However, Nvidia has no immediate plans to release the technology publicly.

The technology joins other AI systems, like those from startups Runway and Meta Platforms, that can generate audio or video from text prompts. Despite the potential applications in the entertainment industry, the relationship between tech companies and Hollywood is strained, with ongoing negotiations about AI use and recent accusations from actress Scarlett Johansson against OpenAI for imitating her voice.

Key takeaways:

  • Nvidia has developed a new artificial intelligence model, Fugatto, that can generate music and modify voices, aimed at music producers, filmmakers, and video game creators.
  • The technology can generate sound effects and music from a text description and can modify existing audio, such as transforming a piano line into a human voice or changing the accent and mood of a spoken word recording.
  • Nvidia does not have immediate plans to publicly release Fugatto.
  • The relationship between tech and Hollywood is tense, with companies like OpenAI negotiating with studios over the use of AI in the entertainment industry, following accusations of voice imitation by actress Scarlett Johansson.
View Full Article

Comments (0)

Be the first to comment!