Intona is an AI powered musical instrument and sound design tool created by Christopher Lock. Intona was built using RAVE (Realtime Audio Variational Autoencoder) by Antoine Caillon and Philippe Esling and nn_tilde.
The Intona.AI repository can be freely pulled from Github via the following link: https://github.com/Chris-Lock-Music/Intona.AI
A link to the RAVE library repository can be found here: https://github.com/acids-ircam/RAVE
Intona was trained on a database of sounds made up from compositions that Christopher has created over the past 5 years, during his time as part of the Harvard Group For New Music, and partially serves as a kind of living portfilio somwhat representitive of his compositional ideas.
Intona is meant to be used in real time as a performance/improvisation instrument or as an on-the-fly sound design tool. When Intona recieves input, it attempts to recreate whatever sounds it takes in but with the texture and sound qualities of the training data, i.e. my compositional output from the past 5 years.
Intona has three different modes of input; a sinewave generator causing Intona to produce drones, audiofile playback causing Intona to mimic the rhythm, pitch and quality of whatever audio file you choose to drop in, and a live mic input allowing you to sing or play an instrument into Intona.
To set up Intona follow these simple steps:
Step 1: Download RAVE from https://github.com/acids-ircam/RAVE
Step 2: Download nn~ https://github.com/acids-ircam/nn_tilde
Step 3: Make sure these packages are in the packages folder of Max/MSP
Step 4: Unzip the file Models.zip into Documents -> Max 8 -> Packages -> nn_tilde -> externals
Now the patch should be all set to run. For technical help with the patch and to download the trained model reach out to chris.lock.music@gmail.com
A video demonstration of Intona can be found below:
This project was made possible with help of Manuel Cherep, 2023.
Christopher Lock is a computer musician, creative programmer, and film composer currently based in Cambridge, MA. He creates densely textural electronic music which slowly mutates and morphs over time and is often saturated with dark imagery or phantasmagoria. His musical practice stems from a tradition of Baltimore area noise music, where he first started experimenting with sound.
Through out his education Christopher has been fortunate to study with such musical visionaries as Esperanza Spalding, Meredith Monk, Vijay Iyer, Claire Chase, Thomas Dolby, Chaya Czernowin, Hans Tutschku.
In the spring of 2022 Christopher was the appointed Teaching Fellow for Esperanza Spalding’s Songwright's Apothecary Lab at Harvard University where he worked with Prof. Spalding and the students intimately during the semester to develop a concert program of new original works.
Christopher is an active composer of film music and has worked with artists such as Ezekiel Goodman (I Know What You Did Last Summer) and Robert Eng (Mullholand Drive, Twin Peaks, Corroline). In January of 2022 Christopher composed original music for Giovanna Molina's Deer Girl which was an official selection for the Sundance Institute's Ignite x Adobe Fellowship.
In the summer of 2019 his audio/visual work, in collaboration with his grandmother (also called Chris Lock), was screened at the Venice Biennale from May 8th to June 4th. The video was projected in the Palazzo Pesaro Papafava as part of the UK's.
In April of 2022 Christopher produced and performed original electronic music for LuChen's debut runway show in Manhattan, which was later reviewed positively by Vogue Magazine, Fashion Week, and other major publications.
Christopher is currently a Ph.D candidate in Music and Computer Science at Harvard University. He holds a Master’s Degree in Computer Music from Harvard, a Bachelors Degree in Computer Music from Johns Hopkins University (Peabody Conservatory), and a second Bachelors degree in viola performance (also from Hopkins).
dark imagery dark imagery dark imagery dark imagery dark imagery dark imagery dark imagery dark imagery dark imagery dark imagery dark imagery dark imagery dark imagery dark imagery dark