[vox-tech] speech synthesis of a browser's window

Peter Jay Salzman vox-tech@lists.lugod.org
Tue, 2 Mar 2004 12:58:59 -0800


On Tue 02 Mar 04, 12:23 PM, Bill Kendrick <nbs@sonic.net> said:
> On Tue, Mar 02, 2004 at 10:21:36AM -0800, Peter Jay Salzman wrote:
> > 
> > has anybody here used this plugin?
> 
> Yes, I've used Konq's speech plugin in the past.  Not sure the absolute
> latest has support for this, though.
> 
> You might consider using Lynx or Links to do this, as well.  Just have it
> dump the rendered HTML as plaintext and then play it with Festival.
> (I think Konq's speech stuff was just a front-end to Festival, anyway).
> 
> Good luck!
> 
> -bill!

hi bill,

thanks for the reply.  i took your advice, and festival is very close to
being good.  the quality is just a *tad* too poor.   here's a page
that i'd like to be read to me:

   http://www.hedweb.com/manworld.htm

[note: there are a few equations that are image files, but my mind can
fill those in, i don't need to be read the equations.]

the problem is that the speech is a bit too poor.  it's quite effective
to listen to while i read along.  my eyes don't have to focus as much,
and they don't get as fatigued as they do when i read long paragraphs on
the screen.

i noticed there are a few voice files.  i installed the 16k higher
quality ones:

p@satan$ dpkg -l "*vox*" | grep -v none
festvox-ellpc1 1.4.0-3    Castilian Spanish male speaker for Festival
festvox-kallpc 1.4.0-4    American English male speaker for festival
festvox-kdlpc1 1.4.0-4    American English male speaker for festival

do you know, offhand, how to tell which voice file i'm using?

any quick tips on improving quality?

thanks!
pete

-- 
Make everything as simple as possible, but no simpler.  -- Albert Einstein
GPG Instructions: http://www.dirac.org/linux/gpg
GPG Fingerprint: B9F1 6CF3 47C4 7CD8 D33E 70A9 A3B9 1945 67EA 951D