Spotify has quickly become a favorite audio streaming service among thousands of users around the world. Expanding its services in the music industry, Spotify opened its Python framework, Pedalboard.

The Pedalboard is a Python library for adding effects to audio and supports many common effects outside of the box. Essentially, it was designed by Spotify’s Audio Intelligence Lab to enable creators to use studio-quality audio effects in Python and TensorFlow.

Deep Learning DevCon 2021 | 23-24th Sep | Register>>

DAWs and the landscape

Until now, music and podcast producers have typically used DAW – a digital audio workstation, software packages that allow them to edit, manipulate, and perfect audio. Currently, they are used in the majority of audios we listen to today, including content on Spotify. However, while DAWs allow musicians flexible performance and improved control over audio quality, they are not made for programmers.

Spotify’s Pedalboard allows programmers to harness the “power, speed and sound quality” of DAWs in their code. Released as a new Python package, Pedalboard meets the criteria to bridge the gap between professional audio software and Python code.

Looking for a job change? Let us help you.

JUCE is the industry standard framework for high performance and reliable audio applications and is the leading framework for cross platform audio applications. The crankset is built on JUCE, which allows it to have remarkable speed and quality. In addition, the built-in convolution operator enables high-quality simulation of speakers and microphones. Finally, the package supports several built-in audio effects, third-party VST3® and Audio Unit plug-ins to increase the sound possibilities.

The pedal board, inspired by the pedal boards used by guitarists, includes the stylistic effects found on the instrument. The programmer has the freedom and control to modify the sounds with these effects and augmentations. The package also offers volume control tools like a noise gate, compressor and limiter; and styling tools like distortion, phaser, filter and reverb. Effects can be saved by grouping plugins into a pedalboard to speed up the process.

Machine learning and footswitch

The Pedalboard is a programmer’s paradise with the ML and content creation related features it has.

Considering its speed, Pedalboard increases the speed of increasing data and guarantees improved results. It can be used on models to increase the size of training data and performance by taking a small set of data and increasing it with audio effects. The engineering team referred to a blog post to state, “The crank has been thoroughly tested in high performance, high reliability ML use cases at Spotify, and is used extensively with TensorFlow.”

It also makes audio effects application scripts accessible with Python codes. This helps automate parts of the audio creation process – a feature that wasn’t available with most tools until now. Additionally, the coding process helps the user to create a workflow command line to apply a third-party plug-in without launching the DAW or importing / exporting audio. This reduces the steps involved in the process with better results.

Creativity is an integral part of the musical creation process, requiring human intervention and not calculation. Pedalboard guarantees that it supports the software for artists and their creativity without hindering it. In fact, musicians and producers only need a little Python knowledge to take advantage of its creative effects. This process would be a long and tedious flow with DAW, but Pedalboard is easier for those new to Python. As a result, Spotify has placed Pedalboard as a bridge between code and music.

The results of tests run on Pedalboard by Spotify revealed that common development hardware is up to 300 times faster than Python audio effects packages on the market today. The company has been using Pedalboard internally to process millions of audio hours for over a year and has now opened up the software. The pedal board is also “stage ready” for macOS, Windows and Linux. Find the code and documentation for Pedalboard on GitHub.

---

Join our Discord server. Be part of an engaging online community. Join here.

---

Subscribe to our newsletter

Receive the latest updates and relevant offers by sharing your email.