Re: [orca-list] gnu-speach?

[Mallard <mallard ilgerone net>]

Hello there,

When I posted my message on this topic, I hadn't seen this thread yet. 
My son told me I should share his discovery on this list, and now I find 
that the thread has been going on for a while...

The GPL I listened to is quite interesting.

The voice is great; very warm, and much better than any so-called 
"high-quality voices" I've heard to this day.

Pronunciation requires work, but I think it has potential.

I love Espeak too, especially the Italian version for Android, which is 
unbeatable in my view, both in terms of responsiveness and clarity. But 
having multiple choices never hurts, especially if they're open source 
choices... So I eally hope someone will take the time to further develop 
this synth. I'm quite impresed, I must say.

Thanks Tony for your work and for sharing this with us.

Ciao,
Ollie




Il 23/10/2015 11:33, Tony Baechler ha scritto:
> I'm coming in late on this, but yes, it's a speech synthesizer and I've
> created a demo for it:
>
> http://classicradio.us/iso/gnuspeech_gpl.mp3
>
> Yes, it can be used now with Speech Dispatcher.  You would use the
> generic module or write a wrapper script.  Based on their example in the
> INSTALL file, something like this should work:
>
> ./gnuspeech_sa -c /usr/share/gnuspeech/data/en -p /tmp/params.txt -o
> /tmp/out.wav "Hello world."
>
> I spent quite a bit of time compiling and testing this.  The Mac version
> is more complete and includes the graphical apps, the accessibility of
> which I have no idea.  The standalone version has very limited
> functionality by comparison, but it does work.  I suspect the Mac
> version sounds better, but I don't know and I don't have a Mac.  I will
> share my 64-bit Ubuntu 14.04.3 compiled binaries if anyone wants them.
> If you want them, write to the address in my signature.  Currently, it's
> English only and has no variants.
>
> On 10/22/2015 3:00 AM, kendell clark wrote:
> > This sounds really interesting. However, looking at the link you posted,
> > I'm not sure if it's a speech synthesizer or some kind of program to
> > generate speech phonemes based on a person's speech. This would also
> > need to be packaged in distros to be meaningfully useful. If this isn't
> > the case now it can of course be fixed if this gets used. The steps
> > would be: 1, a speech-dispatcher module would need to be written to
> > support gnuspeech. 2: some minor code might need to be added to orca if
> > the standard speech-dispatcher API calls aren't enough to support it
> > fully, for example, if it has anything like espeak varients. 3: it would
> > need to be packaged up in popular distros like ubuntu, fedora, arch,e
> > tc. Once this is done it should be possible to use it with orca.--
>
> --------------------
> Tony Baechler, founder, Baechler Access Technology Services
> Putting accessibility at the forefront of technology
> mailto:bats batsupport com
> Phone: 1-619-746-8310   Fax: 1-619-449-9898
> _______________________________________________
> orca-list mailing list
> orca-list gnome org
> https://mail.gnome.org/mailman/listinfo/orca-list
> Orca wiki: https://wiki.gnome.org/Projects/Orca
> Orca documentation: https://help.gnome.org/users/orca/stable/
> GNOME Universal Access guide:
> https://help.gnome.org/users/gnome-help/stable/a11y.html
> Log bugs and feature requests at http://bugzilla.gnome.org