TextAloud Speed Scales and Words per Minute

Moderator: Jim Bretti

Post Reply
Jim Bretti
Posts: 1558
Joined: Wed Oct 29, 2003 11:07 am
Contact:

TextAloud Speed Scales and Words per Minute

Post by Jim Bretti »

TextAloud supports both Sapi4 and Sapi5 speech interfaces, and these interfaces use different speed scales. In the older Sapi4 interface, the speed scale is in words per minute. Default speeds for Sapi4 voices are typically in the 150 to 200 range.

In the newer Sapi5 interface, Microsoft got away from measuring voice speed in words per minute. For Sapi5 voices, 0 is always the default speed, and Microsoft provides a calculation for voice vendors on how to assign speeds between -10 and 10. Anything outside the range of -10 and 10 is not 'officially' supported, but we've seen some voices support speeds outside this range. So in TextAloud we use a range of -30 to 30, where only some voices support all speeds in the range.

Here is a note on voice speed from Sapi5 documentation:
The value can range from -10 to +10. A value of zero sets a voice to speak at its default rate. A value of -10 sets a voice to speak at one-third of its default rate. A value of +10 sets a voice to speak at three times its default rate. Each increment between -10 and +10 is logarithmically distributed such that incrementing or decrementing by 1 is multiplying or dividing the rate by the 10th root of 3 (about 1.1). Values more extreme than -10 and +10 will be passed to an engine. However, SAPI 5-compliant engines may not support such extremes and may clip the rate to the maximum or minimum rate the engine supports.

We may add an update in a future version of TextAloud that calculates and displays words per minute on the fly for Sapi5 voices.
Jim Bretti
NextUp.com
Post Reply