LumenVox Now Offers TTS

LumenVox recently added text-to-speech to its portfolio, signaling a new market opportunity for the company that had been focused on its speech recognition engine.

"Over the years, many LumenVox Speech Engine customers have asked for a text–to–speech (TTS) engine of comparable quality to our other ASR products," the company states on its Web site.

LumenVox currently offers male and female TTS voices in American and U.K. English, and Latin American, U.S., and European Spanish. The company will be adding Australian English, French, and German in the coming months.

The LumenVox TTS Server provides text–to–speech synthesis, turning written text into spoken speech. It supports the Speech Synthesis Markup Language (SSML), a way to format text within XML to control the pronunciation of words, but it can also accept plain text. As with the LumenVox Speech Engine, the primary method of interacting with the TTS Server is through the Media Server.

Some common uses include telephone systems, automotive applications, and programs to assist the disabled. It is particularly useful when reading dynamic data that cannot be pre–recorded, such as text from the Web or a street address from a database.

The TTS Server was developed specifically to work with the LumenVox Media Server, meaning that it can be controlled through MRCP versions 1 or 2, allowing for drop–in replacement of other TTS engines in dozens of various voice platforms supported by LumenVox. It also features an extension of the LumenVox C and C++ application programming interface.

And with the same client/server architecture used by the Speech Engine, it supports a fully distributed environment.