Overview

Out of the box, IDOL Speech Server provides several standard tasks that allow you to run individual processing operations on audio data–for example, speech-to-text or speaker identification. IDOL Speech Server also allows you to run multiple operations in a single task. For example, you might want to perform both speaker identification and speech-to-text on a single audio file. You can create a single task that includes both speech-to-text and speaker identification instead of using two separate actions.


_HP_HTML5_bannerTitle.htm