Piper is a protocol for audio analysis and feature extraction. We propose a data schema and API that can be used to support both remote audio feature extraction services and feature extractors loaded directly into a host application. We provide a means of using existing audio feature extractor
implementations with this protocol. In this talk we demonstrate several use-cases for Piper,
including an “audio notebook” mobile application using Piper modules to analyse recordings; a web service for remote feature extraction; and the refactoring of an existing desktop application, Sonic Visualiser, to communicate with a Piper service using a simple IPC mechanism.