Re: just a newbi problem, want to use festival, not flite with emacspeak

[tcross@xxxxxxxxxxx]

Its nothing to do with how the server is implemented. It is about
finding a vendor who is prepared to sell single runtime licenses. Last
time I checked, the smallest number you could purchase was a bundle of
10 runtime licenses and this came out at a bit more than the cost of
the SDK. 

There has been reports of some sites who have said they are going to
sell single licenses, but last time I checked this was still a plan
and not actually available. 

this issue has been raised a number of times on the list. If you have
details of where you can purchase a single runtime license, it would
be great if you can post the details so that others can take
advantage of it and the details can go into the list archive.

Personally, I don't think $300US is too much to pay for a good quality
stable software TTS for Linux - but then again, I was lucky in that my
employer purchased mine in return for some proof of concept web based
speech demos.

regards,

Tim


T. V. Raman writes:
 > 
 > so why do yu ned the  Viavoice sdk - the waa the emacspeak server
 > is implemented, all  you need is the runtime.
 > 
 > >>>>> "tcross" == tcross  <tcross@xxxxxxxxxxx> writes:
 >     tcross> Just a few points which may be of interest in this
 >     tcross> thread.
 >     tcross> 
 >     tcross> Festival is a very powerful and configurable TTS. It
 >     tcross> can support quite a few different voices and has a
 >     tcross> lot of parameters which can be tweaked to improve
 >     tcross> synthesis. The "out of the box" configuration is a
 >     tcross> general default that is likely to meet most users
 >     tcross> requirements.  However, I found (quite some time ago)
 >     tcross> when playing with festival, I could get better
 >     tcross> performance tweaking some of the settings associated
 >     tcross> with festival and the voice tools. Unfortunately, it
 >     tcross> was a while ago and I dont actually remember what all
 >     tcross> the tweaks were.
 >     tcross> 
 >     tcross> Festival supports voices from other sources and in
 >     tcross> many distributions, you will get different quality
 >     tcross> voices - for example, in Debian, there are both 8k
 >     tcross> and 16k voices for US/UK english. The 8k voices don't
 >     tcross> have the same quality, but will probably give better
 >     tcross> performance on slower machines with less memory.
 >     tcross> 
 >     tcross> Although I've never got around to it, mbrola voices
 >     tcross> are supposed to provide very good quality voices with
 >     tcross> festival. Voices from http://www.cepstral.com can
 >     tcross> also be used with festival - they had a perl script
 >     tcross> on their website that would allow you to import a
 >     tcross> cepstral voice into festival. Cepstral voices are
 >     tcross> good quality, but they lose quality significantly at
 >     tcross> higher voice speaking rates. They are commercial
 >     tcross> voices which you have to pay for, but they do have a
 >     tcross> number of different languages available.
 >     tcross> 
 >     tcross> IMO by far the best software TTS for emacspeak is
 >     tcross> ViaVoice, which you can purchase from
 >     tcross> http://www.wizzardsoftware.com. However, you have to
 >     tcross> purchase the SDK and it costs over $300US.
 >     tcross> 
 >     tcross> Second best for quality of speech is the software
 >     tcross> dectalk. However, this TTS engine does crash
 >     tcross> regularly under emacspeak (it works reliably under
 >     tcross> speech dispatcher, but speech dispatcher is using it
 >     tcross> in its most basic way and does not try to use the
 >     tcross> in-line voice control codes emacspeak uses for voice
 >     tcross> locking etc). The software dectalk is available from
 >     tcross> http://www.fonix.com for about $100US.
 >     tcross> 
 >     tcross> I used the softwar dectalk for quite some time and
 >     tcross> managed to live with the regular crashes - all you
 >     tcross> need to do is a C-e C-s when the TTS stops working
 >     tcross> and verything is restarted. Although a bit annoying,
 >     tcross> it provides good voice quality at high speaking
 >     tcross> rates, which I think is important. I now use it as my
 >     tcross> emergency backup TTS if I don't have a hardware
 >     tcross> synthesiser for backup.
 >     tcross> 
 >     tcross> HTH
 >     tcross> 
 >     tcross> Tim
 >     tcross> 
 >     tcross> 
 >     tcross> 
 >     tcross> 
 >     tcross> 
 >     tcross> 
 >     tcross> Lukas Loehrer writes:
 >     >> 
 >     >> Some observations:
 >     >> 
 >     >> I just tried speech dispatcher with festival again. I am
 >     >> using fspeech dispatcher via speechd-el this time. I am
 >     >> using the packages from Debian unstable.
 >     >> 
 >     >> When using the flite output module of speech dispatcher,
 >     >> responsiveness is the same as with eflite in
 >     >> emacspeak. When using the festival output module in speech
 >     >> dispatcher, some of the problems seen in espeakf go
 >     >> away. Speech stops immediately when it should. However,
 >     >> there is a noticeable pause between the moment a command
 >     >> is issued and the corresponding speech starts. I cannot
 >     >> tell if the pause is silence generated by the tts or if it
 >     >> takes that long for the speech to be synthesized. In the
 >     >> latter case, a faster machine might in fact help.
 >     >> 
 >     >> Thus, it seems that if one is looking for good
 >     >> responsiveness, festival used through either espeakf or
 >     >> speech-dispatcher should not be one's first choice. things
 >     >> look differently if priorities lie with support for
 >     >> multiple voices or languages.
 >     >> 
 >     >> Best regards, Lukas
 >     >> 
 >     >> -----------------------------------------------------------------------------
 >     >> To unsubscribe from the emacspeak list or change your
 >     >> address on the emacspeak list send mail to
 >     >> "emacspeak-request@xxxxxxxxxxx" with a subject of
 >     >> "unsubscribe" or "help"
 >     >> 
 >     tcross> 
 > -- 
 > Tim Cross tcross@xxxxxxxxxxx
 >     tcross> 
 >     tcross> There are two types of people in IT - those who do
 >     tcross> not manage what they understand and those who do not
 >     tcross> understand what they manage.
 >     tcross> 
 >     tcross> -----------------------------------------------------------------------------
 >     tcross> To unsubscribe from the emacspeak list or change your
 >     tcross> address on the emacspeak list send mail to
 >     tcross> "emacspeak-request@xxxxxxxxxxx" with a subject of
 >     tcross> "unsubscribe" or "help"
 > 
 > -- 
 > Best Regards,
 > --raman
 > 
 >       
 > Email:  raman@xxxxxxxxxxx
 > WWW:    http://emacspeak.sf.net/raman/
 > AIM:    emacspeak       GTalk: tv.raman.tv@xxxxxxxxxxx
 > PGP:    http://emacspeak.sf.net/raman/raman-almaden.asc
 > Google: tv+raman 
 > IRC:    irc://irc.freenode.net/#emacs

-- 
Tim Cross
tcross@xxxxxxxxxxx

There are two types of people in IT - those who do not manage what they 
understand and those who do not understand what they manage.

-----------------------------------------------------------------------------
To unsubscribe from the emacspeak list or change your address on the
emacspeak list send mail to "emacspeak-request@xxxxxxxxxxx" with a
subject of "unsubscribe" or "help"