Synthetic Talking E-Book generator

STEB generator

How many Digital Talking Books can you produce a day? What if you could produce a book an hour without even having any persons recording it?

It's possible!

The STEB generator produces a Digital Talking Book using synthetic speech. The production process is very fast. It takes approximately 1 hour to make 8 hours recording with synthetic speech. In particular the result is suitable for products like reference books, indexes, manuals etc.

The STEB generator needs very little human interaction which means very short production time at a lower cost.

The STEB generator features:

• An interface easy to use
• Generation of Digital Talking Books from an XML sourcefile
• No interaction required during the generation process
• Automatic change between speech engines of choice
• Possibility of shifting between more than one speech synthesis if multible languages is required
• Ability to encode the audio output in MPEG II audio layer 3

How to use it?

The STEB generator uses an XML file as a source. In addition to the STEB generator a speech synthesis will be required.

With relatively few steps it is possible to generate a Digital Talking Book with synthetic speech. Choose file to process, target directory, speech engine and job name. Specify in addition meta-data like the name of the publisher (your company) to be included in the final product. Push the start button to execute jobs selected. Without further intervention STEB now produces the digital talking book(s).

Featuring an ActiveX component the STEB generator offers the possibility of customazing an individualized and user oriented interface using e.g. Visual Basic.

The STEB generator is in compliance with the DAISY or NISO standard for Digital Talking Books.

Top | Web-editors