Text to Speech Generator Software
AT&T Labs Text-To-Speech software is free to use and fun to try. The Natural Voices demo product is available at http://www.research.att.com/~ttsweb/tts/demo.php and includes 13 different voices, including male and female, American-, U.K.- and Indian-accented English, German and French. You simply type any text in the text field (300 character limit), and hit the “Speak” or “Download” button which creates a wave file for download. Interestingly, many of the accents sound very convincing due to the natural sound and fluid speech.
The software uses Speech Synthesis Markup Language, and by using optional XML style mark tags, you can modify the normal speech results. For example, the prosody rate tag increases or decreases the speech rate:
<prosody rate=”slow”> this is speaking slowly </prosody>
<prosody rate=”fast”> this is speaking fast </prosody>
<prosody rate=”-50%”> this is 50% slower </prosody>
The break time tag creates pauses: <Break time=”3s”/>
The emphasis level tag puts different types of emphasis on words: <emphasis level=”strong”>
The voice name tag specifies a speaking person from one of the 13 different AT&T voices: <voice name=”mike”>
If you are interested in learning how this software works, watch this 8-minute video I created demonstrating the software and how the tags are used: VIDEO
No related posts.
Discussion Area - Leave a Comment
You must be logged in to post a comment.