NO ONE knows??

Gary Kline kline at thought.org
Mon Oct 5 18:43:49 UTC 2009


On Sun, Oct 04, 2009 at 12:37:54AM +0200, Bernt Hansson wrote:
> Gary Kline skrev:
> 
> >	What I'm looking for is how to use the ``better than the 
> >	default voices''; there are several english languages that
> >	are fairly natural sounding.  Nothing I've googled explain
> >	using the quality voices for FreeBSD.
> >
> >	gary
> 
> http://espeak.sourceforge.net/docindex.html


	Tried/found this before at least once.   The cmdline:

	% espeak mb-en1 "hello"

	outputs the string data that "hello" is composed on.  Following further with 
	the linux example is difficult because there is no "usr/local/share/espeak/en1"
	--neither file nor directory.  I did locate  the 796-byte data file:
	/usr/local/share/espeak/espeak-data/mbrola_ph/en1_phtrans but don't have a clue.

	<OPINION>
	From what I've been able to glean, this mbrola stuff is > ten years old.  Whoever
	was laboring away just  dropped it.  I've dug into this computer generated speech 
	just a tiny bit.  Yes, it is possible to have Very real-sounding voices, nearly 
	human-sounding.  But the complexity is extreme.  No wonder the high-quality voices 
	cost $thousands.
	</OPINION>

	Suggestions?

	gary






-- 
 Gary Kline  kline at thought.org  http://www.thought.org  Public Service Unix
        http://jottings.thought.org   http://transfinite.thought.org
    The 5.67a release of Jottings: http://jottings.thought.org/index.php



More information about the freebsd-questions mailing list