VoiceTextTM Text-To-Speech (TTS) Server
VoiceText™ Text-To-Speech Server is an add-on software component to VoiceText™ TTS Engine that manages multi-thread, multi-voice TTS services in a multi-access/user environment. Using the provided SDK, generally VoiceText™ Text-To-Speech Server is used for building custom server applications such as telephony systems, alert systems, etc.
In addition to the features provided by the VoiceText TTS Engine(s), the following is also provided by VoiceText TTS Server.
Web-based Configuration Panel
VoiceText™ Text-To-Speech Server can be managed through a web-based configuration panel. You can enable/disable TTS Engines, set default speed, volume, sentence pause duration, etc.
Thread-usage can be monitored to see how many concurrent TTS synthesis is occurring at a given time. Visual graph of real-time and historic monitoring is available.
VoiceText™ Text-To-Speech Server’s reporting feature allows you to generate custom reports regarding the number of TTS requests, total input text size, response time, etc.
Multiple Custom Dictionary Utilization and Management
Multiple custom dictionaries can be managed and selected for a given TTS request. This allows you “group” custom pronunciations based on the need.
Speech Synthesis Markup Language (SSML) Support
VoiceText™ Text-To-Speech Server supports SSML that enables users to input text with rich, XML-based markup language for assisting the generation of synthetic speech. SSML is used to provide authors of synthesizable content a standard way to control aspects of speech such as pronunciation, volume, pitch, rate, etc. across different synthesis-capable platforms.
Flexible Data Output Formats
VoiceText™ Text-To-Speech Server currently supports the following formats in 8KHz, 11KHz, and 16KHz sampling rates:
16bit linear PCM
8bit A-law PCM
8bit Mu-law PCM
4bit Dialogic ADPCM
16bit linear PCM Wave
8bit unsigned linear PCM Wave
8bit A-law PCM Wave
8bit Mu-law PCM Wave
ASF (Windows only)
Support of APIs
VoiceText™ supports C, COM, Java, and .NET-based Application Programming Interfaces (APIs).
Windows Server 2000, 2003 or 2008.Linux RHEL 4 or higher (known to work under other RedHat-base distributions, such as Fedora).
|CPU||Dual Processor with 1 GHz or faster|
|RAM||1 GB (depending on the number of channels)|
|Database space||35-900 MB or more depending on the number of VoiceText™ TTS Engines installed.|