Continue

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.

Generate

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.

Interpolate

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 the 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.

Groove

Groove 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.

Drumify

Drumify creates grooves based on the rhythm of any input. It can be used to generate a drum accompaniment to a bassline or melody, or to create a drum track from a tapped rhythm. It works best with performed inputs, but it can also handle quantized clips.

We used the same dataset of drum performances as Groove to train Drumify. However, instead of learning a translation from quantized drum patterns to performances, here we map from rhythms to performances. We extract a rhythm from each performance by removing the pitches and velocities, while keeping the precise timing details. When you provide an input sequence -- be it a melody, bassline, chord progression, or drum pattern -- we extract a rhythm in the same way and have the model turn it into a groove.