Welcome to the IBM Text-To-Speech Demonstration.
This demonstration is being performed using 8-bit u-Law at 8KHz which is what one would hear using a telephone.
IBM's speech synthesis technology, ViaVoice Text-To-Speech, is currently available in many products and platforms:
Please enter the text in the language that you want spoken. The demo will not translate your text.
Requirements for demo: A Java Enabled Browser
Synthesis Type: The Speech synthesis engine and data include capability for a concatenative voice dataset representation as well as for a synthesized voice representation.
Concatenative synthesis: Concatenative synthesis provides a natural sounding synthesized speech. The process involves a professional speaker who has recorded particular sentences and phrases to create a library of sounds that are used to dynamically create synthesized speech. Both male and female voices are available.
Formant synthesis: Formant synthesis uses a rules-based synthesis process. Because Formant text-to-speech is totally synthesized, the resulting voice quality is more mechanical sounding than concatenative text-to-speech. Formant synthesis uses the least system resources of the different IBM text-to-speech options.
If you are using Internet Explorer and only get a large grey box without anything inside it, try the following actions to use the 5th Generation demo:
On Internet Explorer click on TOOLS
Click on INTERNET OPTIONS on the menu bar
Click on the ADVANCED tab.
Look down the listing and select the entry in the Java (Sun) section. For some versions of the browser, it means clicking on the box next to the entry in the Java section which contains Use Java 2 v1.4.2_08 for <applet> (requires restart) entry.
Close and reopen the Internet Explorer browser retry the web site: http://www.ibm.com/software/pervasive/tech/demos/tts.shtml
NOTE: Some users of Internet Explorer may notice a refresh problem with the applet in this demo. If you experience this problem, you can try using Netscape Navigator to view the demo.