Take a look at http://www.ispeech.org/
I implemented Speech-Recognition. The API is well documented and easy.
Am 10.01.2014 21:16, schrieb Jai Rangi:
Hello,
Anyone know good quality text to speach engine for building IVRs for
asterisk. Open-source will be nice, but I wont mind paying for
Here is list of top multi language TTS engines
1. Acapela
2. Ivona
3. Loguendo
4. Cepstral.
As per my information, they all work with open source Asterisk however
please contact with their support for more information
Regards
*Tahir Almas*
Managing Partner
ICT Innovations
Luminvox is one.. There are others out there..
Here's an article by Ward Mundy that might help:http://nerdvittles.com/?p=7448
From: jpra...@gmail.com
Date: Fri, 10 Jan 2014 12:16:43 -0800
To: asterisk-users@lists.digium.com
Subject: [asterisk-users] Text to Speech Engine
Hello,
Anyone know
14:42:27 -0600
Subject: Re: [asterisk-users] Text to Speech Engine
Luminvox is one.. There are others out there..
Here's an article by Ward Mundy that might help:http://nerdvittles.com/?p=7448
From: jpra...@gmail.com
Date: Fri, 10 Jan 2014 12:16:43 -0800
To: asterisk-users@lists.digium.com
, it's got some good info to get you started.
From: tjrl...@live.com
To: asterisk-users@lists.digium.com
Date: Fri, 10 Jan 2014 14:42:27 -0600
Subject: Re: [asterisk-users] Text to Speech Engine
Luminvox is one
On 10/1/14 8:16 pm, Jai Rangi wrote:
Anyone know good quality text to speach engine for building IVRs for
asterisk. Open-source will be nice, but I wont mind paying for thing really
good.
We recently used Ivona for a fairly complex IVR project (multi-lingual,
including pronunciation of
http://translate.google.com/translate_tts?tl=enq=i always find google
translate works well
http://translate.google.com/translate_tts?tl=frq=je trouve toujours google
translate fonctionne bien
On Jan 10, 2014 3:17 PM, Jai Rangi jpra...@gmail.com wrote:
Hello,
Anyone know good quality text to
Thank you every one,
Yes google's translate is really good.
http://zaf.github.io/asterisk-googletts/
But I dont like the fact that have to go over the wire every time. Looking
for some thing to install on local server.
-Jai
On Fri, Jan 10, 2014 at 5:15 PM, Darryl Moore dar...@moores.ca
srinivas Antarvedi wrote:
Hello users,
Actually i wanted to implement Text-To-Speech engine
from cepstral voice using swift application
i tried the documentation of doing this and i was unsuccessful
at doing this work with asterisk
can anybody please help me out finding the solution to
At 03:13 12/5/2007, srinivas Antarvedi wrote:
Hello users,
Actually i wanted to implement Text-To-Speech engine
from cepstral voice using swift application
i tried the documentation of doing this and i was unsuccessful
at doing this work with asterisk
can anybody please help me out finding the
Kevin Savoy a écrit :
Can someone recommend a good text to speech engine that is usable by
Asterisk? I have tried the Festival one and it just doesn’t cut it for
commercial applications.
Have you tried RealSpeak from Nuance (ex Scansoft), available at:
N.B.: Please use plain text when sending to this list
Can someone recommend a good text to speech engine that is usable by Asterisk?
I have tried the Festival one and it just doesn't cut it for commercial
applications.
We are willing to pay for a good one that works. Anyone tried the ATT
Cepstral seems to sound descent...But if you have
more than one voice installed (Example: different languages)
I can't say it in realtime in the dialplan...I have
to do a little trick like:
exten = 1,1,System(/opt/swift/bin/swift -n
Diane-8kHz "Hello World" -o
Discussion
Subject: Re: [asterisk-users] Text to Speech
N.B.: Please use plain text when sending to this list
Can someone recommend a good text to speech engine that is usable by
Asterisk? I have tried the Festival one and it just doesn't cut it for
commercial applications.
We are willing to pay
Quoting Kevin Savoy [EMAIL PROTECTED]:
Can someone recommend a good text to speech engine that is usable by
Asterisk? I have tried the Festival one and it just doesn't cut it for
commercial applications.
I like Cepstral.
Using the information here:
You might try runtime Dectalk for Linux available from
http://www.fonix.com -- its not free, but it sounds quite nice.
on Monday 08/21/2006 Time Bandit([EMAIL PROTECTED]) wrote
N.B.: Please use plain text when sending to this list
Can someone recommend a good text to speech engine that is
Discussion
asterisk-users@lists.digium.com; Kevin Savoy [EMAIL PROTECTED]
Cc: 'Asterisk Users Mailing List - Non-Commercial Discussion'
asterisk-users@lists.digium.com
Sent: Monday, August 21, 2006 5:13 PM
Subject: Re: [asterisk-users] Text to Speech
Quoting Kevin Savoy [EMAIL PROTECTED
All I can find for Flite is for AAH, does it work as well with plain
Asterisk? Is the setup the same?
Never tried it, but it should be the same.
Have a look here : http://dialogpalette.sourceforge.net/extras.html
hth
___
--Bandwidth and Colocation
People working on this have found that context influences the
pronounciation of words. I think the root cause of this is
that the human vocal tract cannot re-shape itself for different
sounds instantly and must move from the previous sound to the next
sound, we hear the movement. If it does
I must say this is basically correct
BUT
Remember that festival is actually based phonetically. remember
that and modify your text accordingly and you might be surprised at the
results.
yes the standard voices do suck !
On Tue, 15 Jul 2003 23:04:24 -0700 (PDT), Chris Albertson wrote:
At 15:41 2003-07-15 -1000, Matthew John Darnell wrote:
Why hasn't someone found 50 people who sound alike, put them in sound
studios and record the 10,000 most commonly used words. You would all
differnent forms of the 1,000 most words, i.e. leading, trailing, question
etc.
You can synthesize the
--- Moshe Yudkowsky [EMAIL PROTECTED] wrote:
SNIP
The real trick is to get the correct posidy. Here's three sentences
with
the same words but each with different prosidy:
I said 'yes.'
I said yes?
_I_ said '_yes_'???!!
Both formative and concatenative systems add prosidy. Adding
At 10:11 2003-07-16 -0700, Chris Albertson wrote:
SNIP
if you want a synthetic voice to sound
natural you will have to tell the software the _intent_ of the words
not just the words. You would need a markup language for that
emph I /emph said quotequestionword yes /quote/questionword
The W3C has
Moshe Yudkowsky wrote:
At 10:11 2003-07-16 -0700, Chris Albertson wrote:
SNIP
if you want a synthetic voice to sound
natural you will have to tell the software the _intent_ of the words
not just the words. You would need a markup language for that
emph I /emph said quotequestionword yes
Matthew John Darnell wrote:
Why hasn't someone found 50 people who sound alike, put them in sound
studios and record the 10,000 most commonly used words. You would all
differnent forms of the 1,000 most words, i.e. leading, trailing, question
etc.
You can synthesize the other 0.05% when you run
25 matches
Mail list logo