A small Javascript library for browser-based real-time speech recognition, which uses Recorderjs for audio capture, and a WebSocket connection to the Kaldi GStreamer server for speech recognition.

Download .zip Download .tar.gz View on GitHub

This page just lists some demos. For more information about the library (incl. the supported browsers) click on "View on GitHub".

  • mob is a basic dictation application with a mobile-friendly layout (English UI, English/Estonian speech recognition)
  • demo is a very basic dictation application (Estonian UI, Estonian speech recognition)
  • diff visualizes recognition accuracy by a textual diff (Estonian UI, Estonian speech recognition)