Generic class that implements the 'play' method for mp3 files

Generic parent class for all STT engines

Generic parent class for all speakers

Abstract base class for Vocabulary classes. Please note that subclasses have to implement the compile_vocabulary() method and set a stri

Speech-To-Text implementation which relies on the AT&T Speech API. This implementation requires an AT&T app_key/app_secret to be present in

Dummy TTS engine that logs phrases with INFO level instead of synthesizing speech.

Uses the eSpeak speech synthesizer included in the Jasper disk image Requires espeak to be available

Uses the festival speech synthesizer Requires festival (text2wave) to be available

Uses the flite speech synthesizer Requires flite to be available

Speech-To-Text implementation which relies on the Google Speech API. This implementation requires a Google API key to be present in profile.

Uses the Google TTS online translator Requires pymad and gTTS to be available

Uses the Ivona Speech Cloud Services. Ivona is a multilingual Text-to-Speech synthesis platform developed by Amazon.

A very basic Speech-to-Text engine using Julius.

Uses the OS X built-in 'say' command

Uses the MARY Text-to-Speech System (MaryTTS) MaryTTS is an open-source, multilingual Text-to-Speech Synthesis platform written in Java.

Uses the svox-pico-tts speech synthesizer Requires pico2wave to be available

The default Speech-to-Text implementation which relies on PocketSphinx.

Speech-To-Text implementation which relies on the Wit.ai Speech API. This implementation requires an Wit.ai Access Token to be present in