zsmith.co

Thoth Speech Recognition App

Revision 1
© 2019 by Zack Smith. All rights reserved.

Introduction

Thoth is my MacOS front-end for the Sphinx speech recognition engine. It listens for sound, records it, converts the sample rate to what Sphinx needs and sends it to Sphinx. It receives the resulting recognized text from Sphinx and displays it in an editable text view.

I'm making it public because there is just no need to keep it closed source any longer. Plus if anyone wants to update it for Kaldi, which is reportedly more up-to-date and more advanced than Sphinx but trickier to use, feel free but please send me the updated source code.

Download

Coming soon.