This article includes a list of general references, but it lacks sufficient corresponding inline citations. (May 2016) |
Original author(s) | lamere ppk96 schnelle wwalker |
---|---|
Initial release | December 14, 2001 |
Stable release | 1.2.2
/ March 9, 2009 |
Written in | Java |
Platform | Java |
Size | 12.8 MB |
Available in | English |
Type | Speech synthesis |
License | BSD |
Website | freetts |
FreeTTS is an open source speech synthesis system written entirely in the Java programming language. It is based upon Flite. FreeTTS is an implementation of Sun's Java Speech API.
FreeTTS supports end-of-speech markers. Gnopernicus uses these in a number of places: to know when text should and should not be interrupted, to better concatenate speech, and to sequence speech in different voices. Benchmarks conducted by Sun in 2002 on Solaris showed that FreeTTS ran two to three times faster than Flite at the time.[1]
As of June 2019, the newest version of that project originates from April 2017. Intensive development finished in March 2009 with release 1.2.2.
Through using some straightforward optimizations and relying on the aggressive optimizations performed by the Java HotSpot compiler, we were pleased to find that FreeTTS runs two to four times faster than its native-C counterpart, Flite. Clearly, it would be possible for us to roll some of these optimizations back into Flite with the likely result of improving Flite's performance to levels similar to FreeTTS. The lack of Java platform features such as garbage collection and high-performance collection utilities, however, makes performing these optimizations in Flite much more time consuming from a programming point of view.