similar to: Cepstral voices

what's the easiest way of using cepstral voices with asterisk ? On their website, in the ssml page (http://www.cepstral.com/cgi-bin/support?page=ssml), they say "Asterisk PBX SSML can be used with Cepstral voices in Asterisk by simply embedding the markup into the input text." what input text ? To what application ? Thanks ! Julian

How do you get Cepstral working, they only offer windows versions. do I have to complie it to linux? http://www.cepstral.com

I'm about to begin working on an ivr project to do database backed scheduling. I would like to use text to speech in some places. What are the differences in using festival vs. Cepstral? How are they similar, how are they different? Is one really better than the other? How and Why? Thanks, Eric -------------- next part -------------- An HTML attachment was scrubbed... URL:

We are having some major problems with app_swift since we went live. It is regularly segfaulting. I don't know if this is my fault or not, but here's the story: Installed the cepstral voices (at the time, 4.0) on our test system (2.6.9-42.0.10.ELsmp) and later added some extra voices (now 4.2). All worked fine - we stress tested (20+ simultaneous calls). Move to live (

I'm using trixbox and the asterisk agi. I downloaded a cepstral voice and worked with it until I got the code to do what I wanted. I then registered the voice today to get rid of the 'this voice is not yet registered", stuff yet it still does that. Any ideas on how to fix this? It told me my info was valid. Thanks! -------------- next part -------------- An HTML attachment was

I just read about the partnership but was wondering what is actually going to happen? Is asterisk going to be bundled with cepstral voices for free :)? Or whats the deal?

Hi, I'm using Cepstral as a TTS Engine for Asterisk with Swift application. It works fine when I have just 1 voice installed. Now I have 2 voices in the same language installed but I can't seem to find the way to select which voice to use in Swift's application in Asterisk. Does anyone know?? Thank you, Pim

Hi all, I hope that I'm not breaking protocol too much by posting a message in this group about a problem that I'm having with an Asterisk Business Edition installation, but the reason that I'm posting here is because the problem that I'm having isn't really with the Business Edition, it is with the Cepstral text to speech product that I'm using with it, and also because

Hello list, I have been using Cepstral's 8KHz voices for my text-to-speech service for some time now, and have been noticing that the voice quality is really poor, doesn't matter what phrase I give it to convert. None of the other 8KHz voices I have ever used were this bad. It doesn't seem good enough system to be used in a commercial system. Is there any better quality text-to-voice

Some of you may know me as ManxPower from #Asterisk at irc.freenode.,net I've posted my demp weather report Asterisk AGI script at http://www.fnords.org/~eric/asterisk/downloads/ I have no affiliation with Cepstral. Below is the README: Contact: Eric Wieling <eric@fnords.org> If you want a demo of this AGI script you may call via IAXtel 1-700-923-3645 extension 2101. Option 23 is

Hello all, I am trying to get cepstral to work with Asterisk for Text to Speech purposes. I got Asterisk to recompile with cepstral and after doing *CLI> show cepstral female voices Available Cepstral voices: Name Gender Age Language Sample Rate License ========== ========= ===== ==================== ============= ============ Amy female 30

Hi All, We just bought a sip based PA setup here with the intention of hooking it into our existing asterisk (1.4) setup. It works as expected when I dial it's extension, but I want to have system generated speech played based on some action (using cepstral, which is already installed and working). My first thought was to DIAL to the extension, and then have cepstral play the audio. The

Hello! I have developed an IVR using AGI and so far it works great. I'm using Cepstral voices, but now want to use the voices from AT & T that are on a Windows server to be heard best. With cepstral what I do is to generate audio files from shipping and this text I reproduce this method it has worked very well. Now, try to do the same by creating the audio file in windows with the

Hi all, i'm trying to integrate cepstral and asterisk, and i have a problem i'd appreciate any help with (i know it's a bit tangential, but i figure this is the place with the most knowledge of app_swift and asterisk). I've installed swift from cepstral.com with alison's voice, and it works fine, from the command line i can do swift "hello there" -o test.wav and then

I'm expirimenting with Cepstral via swift.agi. It loads w/ no problem, but there is a fairly long separation between words -- almost as if it is processing one word at a time, rather than stringing a phrase together. When I run cepstral with a similar script, but not through an actual call from asterisk the separation between words is short and natural. I'd really appreciate

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 I have a license for Allison-8kHz and two concurrent port licenses that I purchased from Cepstral at the end of last year. I just got around to installing to my * 1.6.0.10 machine. I've decided that the best way for me to integrate the two would be res_cepstral, which I downloaded and installed. Everything is fine, except the register program,

I downloaded Cepstral to my Asterisk Box. I did the install and let it install to /opt/swift. I brought down a new CVS-HEAD as of today 10/1. I added APPS+=app_cepstral.so into the Makefile in /usr/src/asterisk/apps/Makefile Like: # Obsolete things... # #APPS+=app_sql_postgres.so #APPS+=app_sql_odbc.so APPS+=app_cepstral.so # I did this piece but wasn't sure exactly what part of the

Hello, I recently purchased the Cepstral 6 text-to-speech engine (swift), and am now wondering if I should have bought something else. I would like to use Cepstral text to speech like some people use the Festival() or Flite() applications. For example, when I do a "core show application flite" at the CLI, flite is available to me: localhost*CLI> core show application flite

Does anyone have any idea on how to force cepstral to convert a number to speech ? I have noticed that sometimes it speaks the number correctly, and at others it doesn't. 1) 787 is pronounced 7-8-7 2) 123 is pronounced one-hundred and twenty-three. 1) is wrong for what i need, 2) is perfect. Is there anyway of forcing numbers to be pronounced as 2) ? I've tried looking at the ssml

If you want to hear an example of the new Cepstral voices (v3.0.2) dial 700-348-3589 I have Frank and Emily available.