Mage is a new software library for using HMM-based speech synthesis in reactive programming environments. It is based on the HTS engine, but instead of using all the available context information for the computation of speech audio samples, Mage can synthesize speech using a limited number of labels preceeding and succeeding the currently synthesized phoneme. It can go as low as only one label of phonetic context, just the current one. Mage brings a realtime audio architecture on the top of HTS and a user-friendly API for developers to integrate reactive speech synthesis in their applications.

watch the tutorial for Xcode

(instructions for linux)


change speech, one sample at a time...