Sakhr Text-To-Speech (TTS) engine converts any Arabic/English text into a human voice. Sakhr has been focusing during the last 8 years on creating an Arabic TTS engine, which can match in its quality the human voice. Final release of Sakhr TTS can convert not only plain text to voice, but it can also convert SSML input text. TTS supports Pronunciation Lexicon Specification (PLS), which is used with SSML to generate synthetic speech in Web and other applications. This technology gives businesses a competitive edge by allowing them to provide their customers with the latest static and dynamic information anytime and anywhere using their telephones and mobiles.

How can a TTS help businesses?
The huge quantity of dynamic data, which people on the move need to check about for their daily activities as news, sports, weather, stock options, bank accounts, e-mails, etc., is on the rise. A business thus needs a powerful TTS engine that converts data into human voice in real time, and at the same time can handle the tremendous load of telephone calls using the latest techniques in load balancing and data streaming.

How can a TTS technology save money and time?
The TTS technology is becoming indispensable to businesses that need to feed their customers with the latest vital information in real time. These businesses usually use IVR (Interactive Voice Response) systems and call centers to communicate this information to their customers and prospects. Converting vital data stored in Websites, databases, and files into human voice using the traditional expensive and time-consuming human studio recordings is a difficult process, since the information is usually dynamic. In some cases, it would be impossible to track these changes using human recordings methods. Only a powerful TTS engine that supports Arabic and English languages can offer the right solution for the information stored in IVR systems and call centers.

Why is an Arabic TTS different?
Arabic is a difficult language and very different from languages such as English, French, or Spanish. Those languages, written in Latin alphabet, have vowels while the Arabic language has special characters called "diacritics". These diacritics give the Arabic words the correct meaning inside a sentence. For example, two Arabic words that have different meanings and are written the same way, only diacritics can help the reader to distinguish between them. Examples of diacritics are: ً َ ُ ٌ For this reason, Sakhr has developed the Diacritizer engine. This engine can insert the diacritics needed in Arabic texts automatically. It is the main component of Arabic TTS. Without the Diacritizer, the output of the TTS engine would be inaccurate and unclear. Since native Arabic speakers write Arabic text without diacritics, the TTS engine should handle the non-diacritized text. The Diacritizer will convert non-diacritized text into a diacritized text, and then the TTS engine converts it to a clear human Arabic voice.

Media Resource Control Protocol (MRCP) Server and Client
Sakhr has developed MRCPv2 Server and Client and integrated its Text-To-Speech engine into the MRCP Server. Using the MRCP protocol, now the user can build his/her application on the MRCP Client and communicate with Sakhr TTS engine integrated into the MRCP Server. Sakhr MRCP is used to control Sakhr TTS Synthesizer using Media Resource Control Protocol Stack.
Sakhr MRCP Server is a standalone application, which allows the MRCP Clients to control Sakhr TTS Synthesizer.
Sakhr MRCP Client is a library, which can be integrated into IVR platforms, IP PBXs, Soft Switches, and Media Gateways to control the media resources of the MRCP Server.

Embedded Text-To-Speech (TTS)