Get Started Demos Blog Research Community

Magenta Studio (Standalone)

This page is for the standalone version of Magenta Studio. If you're looking for the Ableton Live integration instead, click here.

Table of Contents


Magenta Studio is a collection of standalone Electron applications. It contains 4 tools: Continue, Generate, Interpolate, and GrooVAE, which let you use the Magenta models on your MIDI files.

side by side of 4 plugins titled continue, interpolate, groovae and generate 4 bars



  • Currently the applications only work on macOS, but Windows support is coming soon.


Unzip the downloaded file, and double click to launch the application.


File selection

All of the plugins work by choosing one or more files from your file system. Once all of your selections are made, the Generate button will become enabled.

Changing the output folder

By default, the output files will be placed in the same folder as the input. Click on the underlined folder name above the Generate button to change it.


All of the applications have a temperature slider. Temperature is a parameter used for sampling in the last layer of the neural network. You can think of it as controlling randomness: higher values produce more variation and sometimes even chaos, while lower values are more conservative in their predictions.


Melody input is limited to monophonic melodies (one note at a time), and drums input uses this MIDI mapping. Notes outside this range will be mapped to these 9 instruments:

Instrument Pitch
Bass drum/Snare drum 36/38
Closed/Open hi-hat 42/46
Low/Mid/High tom 45/48/50
Crash/Ride cymbal 49/51


Continue uses the predictive power of recurrent neural networks (RNN) to generate notes that are likely to follow your drum beat or melody. Give it an input file and it can extend it by up to 32 measures. This can be helpful for adding variation to a drum beat or creating new material for a melodic track. It typically picks up on things like durations, key signatures and timing. It can be used to produce more random outputs by increasing the temperature.

How to use

Click to select a file (or drag and drop) that you would like to extend, then click Generate. The output files will be added to the output folder you selected.


Generate is similar to Continue, but it generates a 4 bar phrase with no input necessary. Choose the output folder, the number of variations, temperature, and click Generate. This can be helpful for breaking a creative block or as a source of inspiration for an original sample.

Under the hood, Generate uses a Variational Autoencoder (VAE) that has been trained on millions of melodies and rhythms to learn a summarized representation of musical qualities. Generate chooses a random combination of these summarized qualities, and decodes it back to MIDI to produce a new musical file.

How to use

Generate does not require any input files, so the folder selection determines where you’d like the output files to go.


Unlike the other plugins, Interpolate takes two drum beats or two melodies as inputs. It then generates up to 16 files which combine the qualities of these two files. It’s useful for merging musical ideas, or creating a smooth morphing between them.

Interpolate also uses a Variational Autoencoder (VAE) similar to Generate. One way to think of the VAE is as a mapping from MIDI to a compressed space in which similar musical patterns are clustered together. Each of your input patterns is represented by a position on this map. Interpolate draws a line between these positions and returns clips along this line. The number of returned files is set by the “steps” slider.

How to use

Interpolate requires two files, which should be the same length and less than 4 measures.


GrooVAE adjusts the timing and velocity of an input drum pattern to produce the “feel” of a drummer’s performance. This is similar to what a “humanize” plugin does, but achieved in a totally different way.

We recorded 15 hours of real drummers performing on MIDI drum kits. These recordings were quantized, removing all velocity and microtiming and were used to train a neural network to predict the unquantized beats as the output. This is similar to the method used in Google’s automatic language translation, but instead of words we are translating from quantized drum patterns to human performances.

How to use

GrooVAE takes one file as input and creates one file.