AT&T logo

Interactive TTS Demo



A research version of Next-Generation Text-To-Speech (TTS) from AT&T Labs.

Please visit our new commercial web site http://www.naturalvoices.att.com/ for product information, sales, support and demos both live and pre-recorded. We expect to have interactive demos of our Spanish and German TTS available in March, 2002.  

ENTER SOME ENGLISH TEXT and THEN CLICK SUBMIT BELOW:
Words in upper case are spelled rather than pronounced. A period and two spaces forces an end of sentence pause.
blank.gif

VOICE: blank.gif OUTPUT FORMAT: blank.gifSAMPLE RATE*: Hz

§blank.gif

We would like to know if something does not sound quite right. After entering some text and listening to it, click to fill in a form telling us what is mispronounced.

*Note: A sampling rate of 8000 Hz (which implies the basic format) produces telephone quality speech. 11025 Hz provides better quality, and is widely supported. 16000 Hz and 22050 Hz offer the highest quality voice, provided your sound card supports one of these sampling rates.

§ You need Javascript enabled to use this page. To hear the audio output, your machine must have audio hardware and your browser must be configured to play audio files. For help, see the audio entries at the WWW Viewer Test Page.   There is a limit of 30 words per utterance and 40 accesses per day per site.

This page is to be used for demonstration purposes only.   For other use, or to offer comments, suggestions and trouble reports send mail to feedback.   Be sure to give your email address if you would like a reply.   The answers to some common questions can be found on our FAQ page.

For information about our TTS system, please visit our Next Generation TTS page.

For some specialized applications using our TTS, please visit our Say Number and Say Address pages.

© 1998-2001 AT&T

PythonPoweredSmall.gif This page was generated using python-2.1.1 and HTMLgen-2.2.2 Fri Nov 21 16:12:15 2008 GMT.