Share via

Dragon Medical SpeechKit design

  • Article

Dragon Medical SpeechKit has been designed based on our extensive experience in both the medical and speech recognition fields. It's important to be aware of the design when integrating it into your app in order to get the most out of it. Please spend some time with our documentation before implementing it.

Dragon Medical SpeechKit

  • Is platform-independent; our functionality can be used from a wide variety of client platforms: Windows desktop, smartphones, web browsers.
  • Enables you to provide core speech recognition functionality with minimum effort and time.
  • Supports medical report creation via frontend speech recognition.
  • Supports immediate correction/finalization by the end user. The browser and .NET editions also support deferred correction.
  • Uses speech recognition to speed up report creation: voice commands, navigation, etc.
  • Needs reasonable recording times of several words/groups of sentences for good recognition results. This means that speaking single words or very short utterances can lead to poor recognition results.
  • Doesn't require complex integration changes when you upgrade to a new version. All new features are available to your end users without you having to program them in your app.
  • Isn't a medical transcription platform.
  • Supports auto-texts and voice commands to speed up medical report creation.
  • Supports Microsoft RDS, VMware/Omnissa, and Citrix environments.