Discover KO’s journey from media artist to Neutone’s model training specialist, where passion for sound meets cutting-edge AI technology to create unique sonic possibilities.

Meet Liu, the graphic designer crafting Neutone’s visual identity through a simple yet unique language. From logotype updates to T-shirt designs, Liu transforms the company’s story into something tangible while enjoying the collaborative team atmosphere.

This handy guide presents 8 essential considerations for training your own custom Morpho model.

The 1.1 update for Neutone Morpho is now live, and with it comes our long awaited model training service. For the first time ever, the freedom to craft new tone morphing models is available to all in a convenient drag-and-drop interface.

Meet Bogdan, a founding engineer at Neutone, merging AI and music to help artists explore new creative possibilities.

Meet Ise, the visual director at Neutone, shaping its design and typography. Passionate about music and art, he aims to create unique visuals for Neutone’s AI-driven sound tools.

Discover the surprising origin of the iconic 1980s ‘orchestra hit’ sound heard in tracks by Michael Jackson and Duran Duran. This digital sampling revolution began with the Fairlight CMI in 1979, which included pre-sampled sounds from Stravinsky’s “Firebird.” Now, Neutone Morpho and it’s training capabilities promises to transform sound creation once again.

Transform any sound into something new with Neutone Morpho, a real-time Tone Morphing plugin powered by cutting-edge machine learning. This innovative tool captures subtle nuances from your input audio, turning your voice into a violin or your everyday objects into musical instruments. The plugin comes with pre-loaded models, with additional timbres available for purchase.

Meet Nico, a Montreal-based programmer who found his way back to coding after pursuing music production. He’s combining his twin passions while working on Neutone Morpho’s frontend and design, hoping to help artists discover sounds they never knew were possible.

Neutone stands with artists in the AI debate, training models exclusively from open-source or licensed audio with proper attribution. Our mission is to create AI tools that expand creative possibilities, not replace artists or exploit their work.

Meet Mike, an interaction design and visual art student who’s interning at Neutone to explore the intersection of sound and visuals.

Justin brings his unique blend of AI knowledge and musical passion to Neutone, focusing on Marketing, PR, HR, and Project Management during their Public Beta. He’s excited about what Morpho can offer artists—the ability to create entirely new, never-before-imagined sounds through powerful AI models.

Keisuke Nohara is researching musical AI to enhance human-AI collaboration at Neutone. As both a programmer and drummer, he’s passionate about developing Morpho models that can generate unprecedented sound textures for creative expression.

Christopher is a founding engineer at Neutone and PhD researcher focused on audio ML. He builds the open source SDK enabling neural audio models in DAWs, while hoping Neutone Morpho offers artists a fresh perspective on sound design and makes cutting-edge audio research accessible.

Meet Naotake, an AI researcher at Neutone who develops cutting-edge architectures for Neutone Morpho. With a background in AI and music production since high school, he hopes Morpho will inspire artists to discover unexpected sounds and break genre norms.

Matthias, a media artist with expertise in UI programming, is currently finalizing Neutone Morpho while developing the cohesive design identity across all Neutone products. He envisions Neutone creating instruments that feel alive with controllable randomness, striking a balance between complexity and simplicity.

Meet Alfie, an AI Application Engineer at Neutone who blends technical expertise with his passion for guitar and unconventional sound design. He believes neural audio effects bring a welcome touch of chaos to music production, balancing the clinical precision of modern DAWs.

Meet Andrew, the CTO and co-founder of Neutone, who turned his musician’s passion into innovative music tech. Originally a guitar enthusiast, he now leads technical development across Neutone’s projects, bringing cutting-edge AI research to artists for creative exploration.

Meet Nao Tokui, CEO and co-founder of Neutone, whose journey blends AI expertise with a passion for music. Beyond his Ph.D. in computer science and founding the AI and Creativity Lab Qosmo, Nao is a DJ, electronic music producer, and avid surfer who creates AI-powered tools for musicians to craft unique sound textures.

This is the third installment in a series featuring the voices of musicians who use Neutone, an AI-based real-time timbre transfer plugin developed by Neutone. In September 2023, Scott Young visited the Neutone office to provide feedback to the development team. Below is his commentary on the album ‘A Model Within,’ which he created using Neutone and was featured in an Ableton interview. It also includes his perspectives on the future of the music industry. How he came to use Neutone in “A Model Within” Last year, while working on a project, my friend Eames mentioned using Machine Learning to speed things up a bit. So I started checking out IRCAM’s […]

This is the second installment of a series of interviews with musicians who actually use Neutone, an AI-based real-time timbre transfer plug-in originally developed by Qosmo (now Neutone, Inc.). We interviewed Darragh Kelly, a composer using AI a lot in his compositions, about the possibilities of using AI in the context of classical music. You have used AI in many of your compositions. I would like to know more about why you use AI in your compositions and how you came to use AI. About four years ago, I was doing a lot of experimental music stuff and conceptual musical work. And felt like I had kind of reached a wall. […]

This is the first installment of a series of interviews with musicians who actually use Neutone, an AI-based real-time timbre transfer plug-in developed by Qosmo. We interviewed a sound designer Shojiro Nakaoka (https://linktr.ee/shojironakaoka) about how he came to use Neutone and what impression he had of it. Shojiro Nakaoka – Artwork generated from the Lissajous figures of audio signals ➖Please tell us about your musical activities. I compose and design sounds for a variety of platforms, including videos, digital signs, apps, games, and hardware—essentially any medium that requires sound. I think my genre is mainly electronic music, but my work involves more than just straightforward sound playback. I also include […]

Throughout our workshops and tutorials so far we have extensively covered how to implement Neuton models using causal architectures such as networks based on causal convolutions or recurrent neural networks. These are a natural fit for a VST which processes outputs in realtime one buffer at a time without being able to see into the future. However, in some cases we simply don’t have access to the underlying architecture of the network, for example when using pretrained networks. In such cases due to the models not being able to handle causal data by design we will hear clicks and pops in the output audio as in the example below. No […]

Announcing Neutone for Mac V1 Neutone for Mac is going off-beta today, fixing major limitations and bugs. We are happy to see a number of artists have started using the plug-in such as BIGYUKI who is working on his upcoming work using Neutone. Since our beta release in May, we’ve expanded the model library with more RAVE and DDSP models including a beautiful-sounding Choir model and authentic sounding Shakuhachi model. Neutone is no longer limited to a 48kHz sampling rate or 2048 buffer size. We’ve done extensive testing on major Mac OS on both M1/Intel architectures. Unfortunately, the Windows version needs a little more time to develop and we will […]

We’ve released two Colab notebooks for those who want to write your own model for Neutone using RAVE and DDSP!

In this article, we’ll briefly go over how neural networks can be used as a new type of audio effect called timbre transfer. Timbre transfer is an audio effect that changes the timbre of the input audio into some certain style. We’ll cover two recent architectures in this field: DDSP and RAVE. Also, we will look at how you can train your own RAVE models and use them with our VST plugin, neutone. Autoencoders Autoencoders are neural networks that are trained to compress and then reconstruct the input. The network can be split into two parts: encoder and decoder. The encoder compresses (encodes) the data into an intermediate representation (often […]