Neutone – AI Audio Plugin and Community

Bringing the latest AI audio technology to the hands of music creators

2022

  • Screen-Shot-2022-12-05-at-0.13.58
  • Screen-Shot-2022-09-06-at-14.07.39
  • 1209craftalive217
  • Neutone introduction movie

“Neutone” is an audio plugin that enables the use of the latest AI audio models and is a project aimed at providing innovative musical expression.

Until now, there have been significant technological barriers to using AI models in music production. Although the complexity has gradually decreased with the emergence of new machine learning libraries, the number of people who can use them is still limited to a very small percentage of those with programming experience.

The audio plugin “Neutone,” developed in-house, runs in a Digital Audio Workstations (DAWs) and can drive DSP (Digital Sound Processing) models using deep learning in real-time. It is possible to utilize AI in the general music production workflow without requiring programming knowledge.

The use of AI, which was once unaccessible to artists and creators, can now be easily introduced into the creative process through this versatile plugin. Similarly, AI researchers and engineers can easily share and feedback with musicians and artists by newly developed models.

By bringing together researchers, engineers, and artists to co-create, the AI music community will grow and bring about innovative musical expression that has never been witnessed before.

Performances

- 2022.12.8 | MUTEK.JP (Shibuya Stream Hall) - 2022.12.9 | Craft Alive with BIGYUKI (Daikanyama UNIT) - 2023.4.13 | NAMM Show with BIGYUKI (Anaheim Convention Center)

Links

- Neutone Project Website - Neutone Developer SDK - Neutone Discord Channel

Credits

Project Direction: Akira Shibata Concept / Tech Lead, Machine Learning: Nao Tokui Tech Lead, Plugin Front-end: Robin Jungers Back-end: Bogdan Teleaga Tech Lead, Plugin and Architecture: Andrew Fyfe Machine Learning: Christopher Mitcheltree Machine Learning: Naotake Masuda

RAVE algorithm was developed by Antoine Caillon and Philippe Esling, STMS Laboratory (IRCAM, CNRS, Sorbonne University, Ministry of Culture and Communication) and licensed by IRCAM