Salvato in:
Dettagli Bibliografici
Autori principali: Mitcheltree, Christopher, Teleaga, Bogdan, Fyfe, Andrew, Masuda, Naotake, Schäfer, Matthias, Bradic, Alfie, Tokui, Nao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2508.09126
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908486810468352
author Mitcheltree, Christopher
Teleaga, Bogdan
Fyfe, Andrew
Masuda, Naotake
Schäfer, Matthias
Bradic, Alfie
Tokui, Nao
author_facet Mitcheltree, Christopher
Teleaga, Bogdan
Fyfe, Andrew
Masuda, Naotake
Schäfer, Matthias
Bradic, Alfie
Tokui, Nao
contents Neural audio processing has unlocked novel methods of sound transformation and synthesis, yet integrating deep learning models into digital audio workstations (DAWs) remains challenging due to real-time / neural network inference constraints and the complexities of plugin development. In this paper, we introduce the Neutone SDK: an open source framework that streamlines the deployment of PyTorch-based neural audio models for both real-time and offline applications. By encapsulating common challenges such as variable buffer sizes, sample rate conversion, delay compensation, and control parameter handling within a unified, model-agnostic interface, our framework enables seamless interoperability between neural models and host plugins while allowing users to work entirely in Python. We provide a technical overview of the interfaces needed to accomplish this, as well as the corresponding SDK implementations. We also demonstrate the SDK's versatility across applications such as audio effect emulation, timbre transfer, and sample generation, as well as its adoption by researchers, educators, companies, and artists alike. The Neutone SDK is available at https://github.com/Neutone/neutone_sdk
format Preprint
id arxiv_https___arxiv_org_abs_2508_09126
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neutone SDK: An Open Source Framework for Neural Audio Processing
Mitcheltree, Christopher
Teleaga, Bogdan
Fyfe, Andrew
Masuda, Naotake
Schäfer, Matthias
Bradic, Alfie
Tokui, Nao
Sound
Software Engineering
Audio and Speech Processing
Neural audio processing has unlocked novel methods of sound transformation and synthesis, yet integrating deep learning models into digital audio workstations (DAWs) remains challenging due to real-time / neural network inference constraints and the complexities of plugin development. In this paper, we introduce the Neutone SDK: an open source framework that streamlines the deployment of PyTorch-based neural audio models for both real-time and offline applications. By encapsulating common challenges such as variable buffer sizes, sample rate conversion, delay compensation, and control parameter handling within a unified, model-agnostic interface, our framework enables seamless interoperability between neural models and host plugins while allowing users to work entirely in Python. We provide a technical overview of the interfaces needed to accomplish this, as well as the corresponding SDK implementations. We also demonstrate the SDK's versatility across applications such as audio effect emulation, timbre transfer, and sample generation, as well as its adoption by researchers, educators, companies, and artists alike. The Neutone SDK is available at https://github.com/Neutone/neutone_sdk
title Neutone SDK: An Open Source Framework for Neural Audio Processing
topic Sound
Software Engineering
Audio and Speech Processing
url https://arxiv.org/abs/2508.09126