The DialogOS dialogue system

DialogOS is a tool for developing dialogue systems, like Apple Siri, Google Home, or Amazon Echo. The user of a dialogue system speaks questions or commands into a microphone; the dialogue system then performs some actions and speaks back to the user.

Most tools for developing dialogue systems are pretty complicated, and require extensive programming skills. By contrast, DialogOS is designed to make it easy to develop a dialogue system, by simply dragging nodes for speech recognition, speech synthesis, and other actions onto a canvas and connecting them together. In this way, one can develop rather powerful dialogues without any programming.

DialogOS has been used in a variety of projects for university and high-school students, see e.g. here and here. It comes with out-of-the-box speech recognition and synthesis, and is seamlessly integrated with Lego Mindstorms.

At the same time, DialogOS can be easily extended with custom functionality, and can connect to existing software through well-defined programming interfaces. It has been used to build dialogue system prototypes in industry and in academic research projects.

Getting started

Download the DialogOS installer from the link at the top of the page and run it. This will guide you through the installation process. You can be running your first dialogue ten minutes from now.

Documentation

An English manual is available in the Github Wiki.

Developers should check out the Wiki for detailed technical information.

History of DialogOS

DialogOS was originally a commercial system developed by CLT Sprachtechnologie GmbH. The rights were purchased by Saarland University in 2017, and DialogOS was subsequently open-sourced.

The open-source DialogOS runs under Windows, MacOS, and Linux. This is in contrast to the commercial version, which only worked under Windows due to limitations in the speech recognizer.