Google’s AI Synthesizer, NSynth, Makes Never-Before-Heard Sounds


It appears that Google doesn’t stop at search tools, phones, social media, and self-driving cars. This time, it’s coming back in an attempt to revolutionize music!

The tech company is working on a new Artificial Intelligence synthesizer program by the name of NSynth, short for Neural Synthesizer. Currently in development by the team at Google Magenta, NSynth works by analyzing instrumental samples and creating new sounds based off the original ones. The developers explain it better below:

“Unlike a traditional synthesizer which generates audio from hand-designed components like oscillators and wavetables, NSynth uses deep neural networks to generate sounds at the level of individual samples. Learning directly from data, NSynth provides artists with intuitive control over timbre and dynamics and the ability to explore new sounds that would be difficult or impossible to produce with a hand-tuned synthesizer”.

This may just be the beginning. The team explains, “We encourage the broader community to use it as a benchmark and entry point into audio machine learning. We hope that this serves as a building block for future datasets and envision a high-quality multi-note dataset for tasks like generation and transcription that involve learning complex language-like dependencies.” Maybe one day we will be hearing music from big artists made using this a more advanced version of this program!

Feel free to listen to some interesting instrumental samples below. Dive in and read into this further by clicking here.