Search   Contact   Home    
ProductsSupportDownloadsSpeech TechnologyLinksCustomer CommentsFree Stuff


Spacer Image
DTalk Feature Summary
This multiple component set consists of a text-to-speech components to make your applications talk,  and grammar, speech recognition, voice command, and dictation components to make your applications listen and understand. There is also a number of supporting components dialog box and UI components to make speech programming a snap.

The low level speech components offer the greatest flexibility in design while the high level components take the more RAD approach for fast and easy development. NOTE - The following is not a complete list of features, it is only some highlights. For a complete description see the DTalk.hlp file which is available in the demonstration version downloads.


TTTS Low level text to speech - This component offers the most flexibility for speech synthesis.
bulletEasy selection of the speech engine and audio devices. 
bulletSend wave output to speakers, file, direct x or a custom audio output device.
bulletSupport for all engine dialog boxes
bulletComplete control of all attributes including; pitch, realtime, speed and volume
bulletSupport for embedded speech tags
bulletAccess to the internal phoneme strings
TVTxt High level text to speech - Voice text adds higher level functionality including a text to speech "site" for central control of TTS attributes.
bulletCentralized control of all Voice text TTS applications on the system through the voice text site..
bulletEasily pause, resume, rewind, and fast forward output.
bulletIncludes may published events including a visual event for animating the TLip component.
bulletControl of speech priority to resolve conflicts when multiple applications are trying to speak at once.
bulletRuntime control of the voice's speed and pitch
bulletSupport for embedded speech tags
TSR Low level speech recognition - Provides low level access to the SR engine.
bulletOne engine instance can be associated with many TGrammar components
bulletAudio input can be from a microphone, a wave file, Direct X or a custom audio source.
bulletEasy selection of speech engine and audio source.
bulletControl over the various engine attributes of AutoGain, Echo, EnergyFloor, RealTime, Threshold and TimeOut.
bulletSupport for Speaker and Microphone selection and creation.
bulletSupport for all engine dialog boxes
TGrammar  Low level speech recognition grammar- use with TSR to define the grammars for any kind of speech recognition, command and control or dictation.
bulletBuilt in grammar complier
bulletDesign time grammar tester
bulletRuntime lists so grammars can be modified at runtime without out recompiling
bulletUsed for any type of grammar; context free, command and control, continuous dictation, or limited domain.
bulletIndividual grammar rules can be activated or deactivated at runtime.
bulletSupports both native engine and SAPI compiled grammars
bulletSupport for speaker training
bulletComplete recognition results objects are returned in each recognition so, for example, the audio wav of what was spoken can be retained.
TVCmd High level speech recognition for command and control - the fastest way to create a command and control application
bulletVoice menus that can be easily created at either design time or run time.
bulletRuntime lists so voice commands can be modified at runtime without recompiling
bulletSite support for central control of all command and control attributes
bulletCommand menus can be global to the system, only active for a specified window or only listening when the speech engine is asleep
TVDct High level speech recognition for continuous dictation - the fastest way to implement continuous dictation.
bulletInvisible virtual edit box lets you easily keep track of what was said
bulletVisual correction floating dialog
bulletAbility to play back what was said
bulletSupports custom topic and command and control grammars
bulletSupports glossary entries
bulletInverse text normalization
bulletDictation site for central control of all dictation applications
TGramComp  Grammar Compiler - for runtime grammar creation and modification.
bulletFast compiles
bulletSupports runtime lists
bulletOutput to memory, file or OLE stream
bulletInput from memory, file, resource or OLE stream
bulletPhrase parser for special features
TMicWizard  Microphone Setup Wizard - implements the standard SAPI wizard.
TLexicon Allows editing of the lexicon for any of the SR or TTS  speech components
bulletAdd a word
bulletGet a word
bulletRemove a word


A dialog box component to allow the user easy engine mode enumeration and selection.
TAuDevDlg A dialog box component to allow the user easy audio device enumeration and selection.
TLip  Animated graphic lips that can respond to text to speech events.
bulletAdjustable lip, tongue, throat, and teeth color
bulletMale or female mouth shape
bulletHigh and low resolution lips

In addition the the above components DTalk comes with extensive documentation and a number of sample projects.


Top of Page


E-Mail us  
  Search | Contact | Products | Services & Support | Downloads | Speech | Links | Comments
Last updated October 20, 2005
© 1999, 2000 O&A Productions