VoiceGenie clearly speaks with VoiceXML

Telephone voice services for traveling professionals or for customer-service applications are becoming more and more popular. IVR (interactive voice response) is the current technology– and it works — but IVR systems require their own infrastructure and skill set, which can be difficult to justify when most enterprises must also support Web initiatives.

VoiceXML eases this problem because voice applications can reside on today’s Web servers and be maintained by IT administrators. To round out a fully functioning voice platform, companies also need a VoiceXML interpreter. One such product is VoiceGenie Technologies Inc.’s VoiceXML Gateway Version 4.5. It provides markup tags modeled after Web languages, and its VoiceXML Interpreter controls speech functions and the associated telephony equipment and speech engines.

Once a company places a VoiceXML application on its Web server, the VoiceGenie VoiceXML Gateway system answers phone calls, processes the voice commands, and delivers the spoken results back to the caller. The VoiceXML application and, say, the inventory database, can reside on the same Web server, simplifying a company’s infrastructure. The standard design of the gateway means IT administrators don’t have to worry about integrating disparate proprietary components to work with the VoiceXML application.

The only piece missing from this gateway solution is VoIP (voice over IP), which VoiceGenie included in Version 5.0, scheduled to ship early this month. Despite this shortcoming, VoiceGenie’s gateway supports multiple speech engines, has a very strong VoiceXML 1.0-compliant interpreter, and is easy to implement, earning it a Very Good score.

We tested VoiceGenie VoiceXML Gateway running SpeechWorks International’s Speechify 1.1 TTS (text-to-speech) software and Nuance Communications’ Nuance 7.0.4 speech recognition engine. With four TTS channels on a Pentium II CPU with 256MB of memory, the gateway responds quickly, taking less than one second to play back initial audio. This is especially good performance when you consider the large amount of memory and CPU resources that speech files generally consume.

For companies that don’t want to make a hardware investment right away, VoiceGenie recently introduced GenieHosting.com, a cost-effective ASP (application service provider) service that offers all the features of the gateway.

A VoiceXML interpreter is one of the most critical parts of any VoiceXML solution because it must precisely execute VoiceXML commands. To evaluate VoiceGenie’s interpreter, we used a stock-quote lookup and a read-back application to test the majority of VoiceXML’s 47 tags and 187 attributes. Some of these specifications can be very difficult to implement, but the VoiceGenie VoiceXML interpreter properly handled each tag and attribute. VoiceGenie plans to update its interpreter to meet VoiceXML 2.0 standards once the 2.0 specifications are finalized.

The open design of this product is another strength. The SpeechWorks and Nuance software plug-ins delivered exceptional TTS and speech recognition, provided clear read-back of our text, and hardly ever misunderstood our spoken input. You can also choose to install other engines, such as the AT&T Watson TTS module.

VoiceGenie VoiceXML Gateway allows a company to reuse its existing Web infrastructure. Organizations can also move away from proprietary IVR systems and their prohibitive setup and development costs. The flexibility that VoiceXML provides in personalizing Web content delivered via wired and wireless devices offers companies a competitive advantage today that employees, partners, and customers will expect in the near future.

Mike Heck ([email protected]) is a contributing editor who builds Web and intranet sites for Unisys in Blue Bell, Pa.


VoiceGenie VoiceXML Gateway 4.5

Business Case: This VoiceXML gateway enables enterprises to quickly and economically deploy VoiceXML applications, thereby providing customers and supply-chain partners with convenient access to crucial business data from any telephone.

Technology Case: Constructed from telco-grade components, the VoiceGenie VoiceXML Gateway’s hardware handles as many as 24,000 ports, and the VoiceXML interpreter fully supports all VoiceXML 1.0 tags. The gateway retrieves and processes both static and dynamic VoiceXML pages from any Web server.


+ Scales up to 24,000 ports (1,000 T1 lines)

+ Has VoiceXML browser and interpreter

+ Conforms 100 percent to VoiceXML 1.0 specification

+ Includes Automatic Speech Recognition and Text-To-Speech capabilities


– Will not offer VoIP until follow-up release

Cost: $2025 per port; volume and reseller discounts available

Platform(s): SCO UnixWare, SCO Open Server

VoiceGenie Technologies Inc., Toronto; (416) 736-0905, www.voicegenie.com

Would you recommend this article?


Thanks for taking the time to let us know what you think of this article!
We'd love to hear your opinion about this or any other story you read in our publication.

Jim Love, Chief Content Officer, IT World Canada

Featured Download

Featured Articles

Cybersecurity in 2024: Priorities and challenges for Canadian organizations 

By Derek Manky As predictions for 2024 point to the continued expansion...

Survey shows generative AI is a top priority for Canadian corporate leaders.

Leaders are devoting significant budget to generative AI for 2024 Canadian corporate...

Related Tech News

Tech Jobs

Our experienced team of journalists and bloggers bring you engaging in-depth interviews, videos and content targeted to IT professionals and line-of-business executives.

Tech Companies Hiring Right Now