gravy.fm
endless intelligent down-tempo radio
Gravy.fm is a long running experiment in audio analysis. Music is deconstructed into raw data and acoustic characteristics. Harmony, tempo, structure and other data points drive a custom playlist engine. Using listener statistics and social trends attached to time zones the engine attempts to evolve. This iteration is focused on ambient down-tempo electronica. There are others if you hunt hard enough, ask Susan. Technologies used include FMOD ,Python, Echo Nest (RIP), Last.fm .net, MySql and Shoutcast/Radionomy group.
Have a listen, Mr Gravy.
acoustic analysis
tracks are automatically analysed for tempo, harmonics, structural characteristics and more. built in a bunker in Bern, Switzerland
AI playlist engine
playlists evolve intelligently; building energy, dropping for rest or plateauing for periods to create a unique listening experience
feedback loop
a custom-built feedback engine monitors listener habits and trends across time zones to automatically adjust the output in real-time