Speech technologies provider Loquendo
offers system integrators reliable, easy to use solutions in a number of languages and in both male and female voices.
Their TTS engine works to convert text to lifelike, natural sounding audio that can help bring multilingual flexibility and audio variety to voice applications. The solution is capable of reading all kinds of dynamic data and prompts in any environment.
Now, the company has announced an all new version of its Speech Engine and SDK with a number of added features and functionalities.
Along with this, the company has also announced new versions of Loquendo (News
) TTS in 10 major languages including: English (US & UK), German, Portuguese, Spanish, Turkish, Polish, French, Italian, Swedish and Dutch.
To give prompt designers more control, the latest version includes an all new set of commands and control tags that allow prompt designers to precisely define how Loquendo TTS reads text, data, navigation commands, Web pages, emails, SMS, etc.
This makes it much easier for developers adopting TTS in vertical markets like automotive, banking and finance because it allows them to select a specific reading mode based on the context so that even the most complex messages are read correctly. This means reading measuring units based on the international standards, time and currency defined for each language and being able to read automotive abbreviations or SMS abbreviations is possible.
In addition, the new version of the TTS engine includes improvements to the way users are able to manage and create lexicons, and more.
Also, the company notes that a new Java client library was created to simplify the development of applications for the Web by providing remote access to Text-to-Speech in distributed applications.
Earlier this week, the company also announced
the release of its version 7.1.0 of its VoxNauta VoiceXML (News
) /CCXML platform for developing multi-lingual, multi-voice IVRs and speech-enabled apps.
With the offering, service developers can improve the impact of interactions through better management of user input and by bringing together synthetic speech with pre-recorded messages, music and special effects.
Stefania Viscusi is an assignment editor for TMCnet, covering VoIP, CRM, call center and wireless technologies. To read more of Stefania’s articles, please visit her columnist page.
Edited by Stefania Viscusi