Wizzard Software Corporation > Wizzard Voice Tools SDK for IBM ViaVoice SMAPI, Speech Recognition

HOME ORDERING SUPPORT PRESS RELEASES

	Intel™ processor or equivalent
	32 MB RAM
	5 MB of hard drive space
	NT, 95, 98, Me, 2000, XP
	Full-duplex, 100% SB compatible sound card
	IBM SMAPI voice recognition and/or TTS engine
	Web or application programming environment (language)

Price: $350.00

About Voice Tools

Voice Tools is a voice interaction development toolset that can be applied to new or existing programs, enabling you to add voice interaction in a familiar programming environment. They were designed to give software programmers the ability to add speech recognition (listen) and text-to-speech capabilities (talk), using IBM's Speech Manager API standard and ECI for Windows (SMAPI), to most software and web applications in just a few hours. Our Voice Tools product line has won Visual Basic Programmer's Journal award as the top speech tools for two years running. Voice Tools will do most of the development work, voice activating your desktop or web application while you benefit from rapid design time, drag and drop construction, seamless integration, testing and maintenance. Our Voice Tools eliminate the need for you to directly interface with the speech engines at the API level which allows for faster development and delivery time. Whether you are voice enabling an existing application or creating one from scratch, you can now add voice commands, open voice dictation, voice prompting and voice navigation directly into your Windows and web applications.

Using the power and flexibility of our Voice Tools, you have full control of the voice interface interaction: From simple button and page navigation by voice to interactively selecting items from lists, to free dictation with full correction and playback capabilities, our Voice Tools deliver what you need to add the power of speech to your application. While retaining all standard Windows properties, text boxes can be designed for interactive voice dictation sessions, list boxes can verbally report their contents, and all types of buttons and tabs can be "clicked" by voice.

Voice Tools Includes

		Speech Recognition and Text-to-Speech component software in ActiveX/COM OCX (controls) and DLL (objects) formats

		Sample applications written in Visual Basic and VBScript

		IBM Speech Recognition Engine (For Internal Development Only)

		IBM Text To Speech Engine (For Internal Development Only) - Optional

Licenses for Commercial Distribution

	For VTK distribution licenses, please fill out the runtime questionnaire found on the Wizzard website or call Wizzard Sales at 954-678-4155 with your usage scenario and a sales professional will be able to answer your questions. (Unlimited (VTK) Distribution License) Price $500.00

	ViaVoice Runtimes: Applications developed with the SMAPI Voice Tools require a runtime version of the IBM ViaVoice Speech Engine. The runtimes contain the speech engine and data files to be integrated with your application package. Click here to fill out the questionnaire.

Detailed Voice Tools Description

For voice driven applications and web pages, the mouse and keyboard can be used in combination with your voice for a more productive user interface. There is no impact on ability to use the mouse or keyboard when adding speech to your application!

Even the most powerful and robust speech APIs on the market don't provide the application framework or support needed to create and maintain high quality voice interfaces. Our Voice Tools do! Voice Tools support IBM's Speech Manager API.

It includes everything you need to create great speech-enabled applications with IBM's SMAPI on Windows 98, Me, NT, 2000 or XP. Rapidly integrate speech technology and deploy speech aware applications and web sites using your favorite development environment: Visual Basic, Visual C++, Visual FoxPro, Delphi, JavaScript, VBScript and all other languages which support use of ActiveX/COM objects.

List of all visual controls

The SMAPI Sonar control makes everything work. It allows navigation by voice within an application developed with Voice Tools. All controls send information to the Sonar Tool, which in turn communicates directly with the SMAPI compatible ASR and TTS engine, sending and receiving information as needed. The SMAPI Sonar control automatically voice enables most other Voice Tools controls, however, SMAPI Sonar can also voice-enable pre-defined keyboard commands, regular buttons, option-buttons (also called radio buttons), checkboxes, menu items (file, edit, view, etc). Additionally, it has built-in navigational commands (to move between fields), commands for microphone manipulations, text selections and corrections. All features are enabled by default, but can be turned off at design time or run time.

SMAPI Map control is used for a "What Can I Say" list. It provides a display of all commands currently available to the end user by voice. You may want to put this on the form if you want the end user to know all the different words or phrases they can speak at any specific point. The control is re-sizable and has scrolling capabilities which are automatically enabled when the list becomes larger. This is a key component in any speech enabled application!

The SMAPI List control acts as a standard list box and allows the end user to select items by voice. Each item may consist of one or more words. Each SMAPI List may have thousands of items for use with such things as an address book or items in a database.

The SMAPI Combo control acts as a standard combo box (also called drop-down list) and allows the end user to select items by voice. Each item might consist of one or more words. Each SMAPI Combo may have thousands of items for use with such things as an address book or items in a database.

The SMAPI Text control acts as a standard text box and allows the end user to dictate text by voice in addition to allowing traditional input through the keyboard. No special voice commands are required by the user. All grammar structures, capitalization, dates and number formatting, etc. are added automatically by the speech recognition engine with the exception of punctuation marks.

The SMAPI Grammar control can help a developer create speech templates with dynamically created word lists that allow tremendous flexibility. They allow for multiple word input and create a feeling of natural language understanding and sophisticated intelligence for your application.

The SMAPI (ECI) Voice control allows developers to provide synthesized voice feedback for the end user through the default TTS engine's speakers. This control allows you to verbally interact with the end user and allows for eyes free computing. Great for patient interaction, call center operators, and hands-on mechanical technicians.

The SMAPI Engines control allows the end user to set a default speech recognition engine. At run time, the SMAPI Engines control will show all the available SMAPI compatible speech recognition engines detected on the end users computer. To make a specific engine the default engine the user can click the checkbox on the left of the name of the preferred engine. The engine will immediately become the default engine and will be placed on the top of the list. With speech engines now coming standard with WindowsXP, MS OfficeXP and AOL, the ability to select a specific speech engine is a critical component to reaching high speech recognition accuracy and achieving the productivity increases available through the use of speech recognition.

The SMAPI Users control allows the end user to set a default user profile. Most SMAPI compatible speech recognition engines allow thousands of user's voice files to be stored on the same computer. At run time, the SMAPI Users control will show all available user profiles detected on the end users computer.

The SMAPI Lexicons control allows the end user to set a default lexicon (most SMAPI compatible speech recognition engines allow for more than one lexicon to be registered on the same computer). At run time, the SMAPI Lexicons control will show all of the available lexicons detected on the end users computer. To make any lexicon the default lexicon single click the checkbox on the left of the lexicon name. The lexicon will immediately become the default lexicon and will be relocated to the top of the list.

The SMAPI Speakers control allows the end user to set a default speaker within the default SMAPI compatible Text-To-Speech engine. At run time, the SMAPI Speakers control will show all available speakers detected on the end users computer. To make any speaker the default speaker, single click the checkbox to left to the name of the speaker. The speaker will then immediately become the default speaker and will then be relocated to the top of the list.

In addition to the controls above, Voice Tools also come with many powerful programming objects. These objects give you even more control over SAPI speech recognition engines and Text To Speech Engine Properties. They give you the power to associate voice commands with blocks of scripts to control remote applications as well as the ability to attach XMLs to speech recognition sessions. The objects give you the ability to alter speech recognition results "on the fly", provide for a more sophisticated error tracking system and many more features and functions. These tools have been created as a result of six years of hard core speech recognition programming experience and many successful application deployments and are the tools our internal programmers use to create sophisticated speech applications for hospitals, law enforcement, financial institutions and more.

If you have any questions after reviewing the following information, please don't hesitate to contact us.

Wizzard Software has been building and assisting developers in building speech applications for eight years and we can help you with your project in a variety of ways.