JSAPI and MBROLA

I'm playing with a speech synthesizer program and I've got it working with FreeTTS just fine.
Of course I want to try some better voices so I'm trying to get MBROLA working and that's where I run into problems. I'm trying to test it using the Player demo program that comes with FreeTTS. I invoke it with this command line:
java -Dmbrola.base="C:\Program Files\Mbrola Tools" -cp Player.jar;jsapi.jar;freetts.jar Player
The player comes up and the following voices are displayed in the Voice ComboBox:
kevin
kevin16
mbrola_us1
mbrola_us2
mbrola_us3
As long as I only select kevin or kevin16 it all works fine but if I select any of the MBROLA voices I get this stack trace:
Exception in thread "Thread-4" java.lang.Error: No audio data read
at de.dfki.lt.freetts.mbrola.MbrolaCaller.processUtterance(MbrolaCaller.java:134)
at com.sun.speech.freetts.Voice.runProcessor(Voice.java:557)
at com.sun.speech.freetts.Voice.processUtterance(Voice.java:402)
at com.sun.speech.freetts.Voice.speak(Voice.java:284)
at com.sun.speech.freetts.jsapi.FreeTTSSynthesizer$OutputHandler.outputItem(FreeTTSSynthesizer.java:705)
at com.sun.speech.freetts.jsapi.FreeTTSSynthesizer$OutputHandler.run(FreeTTSSynthesizer.java:632)
Obviously I'm running on Windows but according to what I've read this is supposed to work on Windows.
Any ideas?

[email protected] wrote:
> Hi,
>
> I am using the following book to learn Eclipse 3.5;
>
> Professional Eclipse 3 for Java Developers by Berthold Daum.
>
> I get the following error when I compile an example that illustrates the
> use of FreeTTS and the JSAPI:
>
> System property "mbrola.base" is undefined. Will not use MBROLA voices.
>
> How would I define "mbrola.base" for FreeTTS through Eclipse. The book
> did not mention anything about setting up mbrola.
> Please help.
> Thank you.
I don't know anything about that book or about MBROLA; you might want to contact
the author of the book.
But to set a system property when running a Java app, you typically pass a "-D"
argument on the command line, or in the Eclipse launch configuration. For
instance, -Dmbrola.base or -Dmbrola.base=whatever .

Similar Messages

Help with JSAPI and JSGF

Hi, i'm working with JSAPI using a JSGF dictionary, the Speech Recognition works fine with the words of the dictionary, but when I say a different word to the saved in the dictionary, JSAPI recognizes them as the word that most closely matches the dictionary, and I need to simply not recognize them, thanks a lot for the help.

Hello,
The dictionary has many many words in it.
You should edit your grammar in order to limit the answers you get as Best_Match_Result.
Also you could add your own words in the dictionary by creating the extra words. In order to do that you should be limited and use the sounds as they are already written in the dictionary. (eg there is on OO sound, but OW) I am not sure if you can add your extra own sounds but you could try it :)
Hope this help,
Marios

Program Sonification (using FreeTTS and MBROLA voices)

I've just uploaded an online chapter (with code) on program sonification -- that's the conversion of an executing program into audio. I've used a mix of spoken words, MIDI note generation, and audio clips.
Part of the application includes an explanation of how to get FreeTTS up and running, and how to add three US voices from the MBROLA site.
The FreeTTS code is quite separate from the rest of the sonification application, and includes two simple examples -- code to list all installed voices, and code to say a sentence input by the user.
The online chapter is at my Killer Game Programming in Java website:
http://fivedots.coe.psu.ac.th/~ad/jg/
It's chapter "Java Art Chapter 5. Program Sonification", located about half way down the page.
Comments are appreciated.
- Andrew
Edited by: AndrewDavison on May 3, 2009 7:13 PM

you will have to explain abit more concerning what you do for nothing to happen and also tell any errors messages that occur.
does it compile successfully? does it create a class file?
if you are posting code use the [ CODE ] tags , its easier to read.

Jsapi speehc synthesizer and recognizer

Hello friends, Have any one of u done a project on speech synthesizer and recognizer using jsapi and Freetts...???

(contd..) to previous thread step5
//testing
u can find so many examples in the net though iam giving one below!!
Class name is Main.java
code follows
package tts; // my package
import java.util.Locale;
import javax.speech.Central;
import javax.speech.synthesis.Synthesizer;
import javax.speech.synthesis.SynthesizerModeDesc;
import javax.speech.synthesis.Voice;
import java.io.*;
import java.lang.*;
* @author Administrator
public class Main {
* @param args the command line arguments
public static void main(String[] args) {
System.out.println("args==" + args.toString());
String voiceName = (args.length > 0)
? args[0]
: "kevin16";
voiceName = new String("kevin16");
System.out.println("Voice Name is :" + voiceName);
//System.out.println("Using voice: " + voiceName);
try {
System.out.println("---1---");
/* Find a synthesizer that has the general domain voice
* we are looking for. NOTE: this uses the Central class
* of JSAPI to find a Synthesizer. The Central class
* expects to find a speech.properties file in user.home
* or java.home/lib.
* If your situation doesn't allow you to set up a
* speech.properties file, you can circumvent the Central
* class and do a very non-JSAPI thing by talking to
* FreeTTSEngineCentral directly. See the WebStartClock
* demo for an example of how to do this.
SynthesizerModeDesc desc = new SynthesizerModeDesc(
null, // engine name
"general", // mode name
Locale.US, // locale
null, // running
null); // voice
System.out.println("--2--");
Synthesizer synthesizer = Central.createSynthesizer(desc);
/* Just an informational message to guide users that didn't
* set up their speech.properties file.
System.out.println("--3--");
if (synthesizer == null) {
System.out.println("--3(1)--");
// System.err.println(noSynthesizerMessage());
System.exit(1);
System.out.println("--4--");
/* Get the synthesizer ready to speak
synthesizer.allocate();
synthesizer.resume();
/* Choose the voice.
desc = (SynthesizerModeDesc) synthesizer.getEngineModeDesc();
Voice[] voices = desc.getVoices();
Voice voice = null;
System.out.println("Length :" + voices.length);
for (int i = 0; i < voices.length; i++) {
if (voices.getName().equals(voiceName)) {
voice = voices[i];
System.out.println("voice " + voice);
break;
if (voice == null) {
System.err.println(
"Synthesizer does not have a voice named " + voiceName + ".");
System.exit(1);
synthesizer.getSynthesizerProperties().setVoice(voice);
System.out.println("going 2 play");
/* The the synthesizer to speak and wait for it to
* complete.
//synthesizer.speakPlainText("Hello world!,iam vijay testing Freetts", null);
String str = new String("heloo world");
System.out.println("String is ....: " + str);
synthesizer.speakPlainText(str, null);
synthesizer.waitEngineState(Synthesizer.QUEUE_EMPTY);
/* Clean up and leave.
synthesizer.deallocate();
System.exit(0);
} catch (Exception e) {
e.printStackTrace();
// TODO code application logic here
@Override
protected Object clone() throws CloneNotSupportedException {
return super.clone();
@Override
public boolean equals(Object obj) {
return super.equals(obj);
@Override
protected void finalize() throws Throwable {
super.finalize();
@Override
public int hashCode() {
return super.hashCode();
@Override
public String toString() {
return super.toString();
here we are using Kelvin16 as voice type..
still u have any problem during the running ... let me know

JSAPI - other languages than English; MIDlet - settings loading; JSAPI - al

Hello!
I need to create application which uses speech recognition. At first I thought about using CMU Sphinx (PocketSphinx or, possibly, Sphinx4). Later I thought about JSAPI. (Sphinx somehow uses JSAPI but I don't know what is the difference between JSAPI and Sphinx).
I have read almost all (up to 6.7.9) of the following tutorial: http://java.sun.com/products/java-media/speech/forDevelopers/jsapi-guide.pdf. Unfortunately I couldn't've found one important thing, i.e. how to create acoustic model for other language than English?
Thanks in advance for your answers :-)!
PS There are some other things which I'd like to know:
1) How to load some settings from file (I guess nowadays configuration files are created with the use of XML but I dunno)?
2) How to maintain algorithm which is used by MIDlet which involves JSAPI? I mean there are some different things which my MIDlet needs to do. I guess it is good habit to divide different goals into separate parts of code (due to object-oriented programming).
     In my case there are some different things:
     a) speech recognition of audio input, i.e. changing input audio stream into output text string
     b) analysis of that text string and according to this string choosing the proper transition in my algorithm
     In general I have written my algorithm on sheet of paper and it takes about ten A4 sheets of paper. Because of it I thought there should be some way to write this algoritm maybe outside the code, in some kind of file which would contain this algorithm. Maybe there is other good way to implement this algorithm, not necesarilly in the code.
     c) sending of results through httpconnection with the use of POST method
     d) receiving in on TomCat on server
3) Which method should I use to receive the recognized speech? I found these:
     a) FinalRuleResult, b) Result -> getBestToken, c) getSpokenText, d) ResultToken of RuleGrammar
4) Can you give me any full examples of JSAPI usage? (Not just short parts of code like in this JSAPI guide)?
Greetins :-)!

Praveen, Yes the infoobject is language dependent. The problem did not happen in BWQ but came up in BWP. so I am not sure at this time what is causing in production that didn't happen in BWQ.
Thanks,
Syed.

Query regarding speech and telephony api

hello everybody,
i am thinking of doing my academic project in java. according to the project requirement i need to call a phone (pstn or mobile) from a pc and give a voice message to the receiver of the phone call. i thought of doing it with java speech api and telephony api. i would also like to know about javaphone api , java communications api and media framework. can the objective be achieved using the latter three? or do i have to go for speech and telephony api only. i am really confused. please guide me.
where can i download jtapi library?
also suggest some good tutorial for jsapi and jtapi.
Thank you.
Sriram K

hi
i'm also doing my project using jtapi.
u can download JTAPI java files then compile it .u ll get the class file.if u know more about jtapi means mail [email protected]

How to take back resources from speech engine

i make an application in swing in which i use jsapi text to speech which read and speak the selected file.
but when synthesizer starts speaking it takes all resources back from jframe hence buttons not worked till speech completed thats why i am unable to use stop button .
and if possible also give me detail how to read pdf's doc,.... files ..
Thanx

Sam_from_India wrote:
by freetts and jsapi i am reading files by io and spoken by jsapi and it worked . but when i select pdf or doc file java.io cant read doc or pdf normaly because these files are encoded hence unable to speak right ....There is no simple general method to extract the 'text' from all file types since most file types such as 'doc' files and 'pdf' files have markup that indicates how they should be formatted. For each different file type you will need to find a library that can read and interpret the file. PDF can be read using iText and 'doc' files can be read using Apache POI but in both there are limitations as to what they can accept.
P.S. I have used FreeTTS for one project. Works great except when the text contains abbreviations or slang.

[solved] espeak error - no sound

hi archfriends,
i installed espeak and mbrola and tried,
#: espeak "hello"
ALSA lib pcm_dsnoop.c:618:(snd_pcm_dsnoop_open) unable to open slave
ALSA lib pcm_dmix.c:1022:(snd_pcm_dmix_open) unable to open slave
ALSA lib pcm.c:2239:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear
ALSA lib pcm.c:2239:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.center_lfe
ALSA lib pcm.c:2239:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.side
ALSA lib pulse.c:243:(pulse_connect) PulseAudio: Unable to connect: Connection refused
ALSA lib pulse.c:243:(pulse_connect) PulseAudio: Unable to connect: Connection refused
ALSA lib pcm_dmix.c:1022:(snd_pcm_dmix_open) unable to open slave
connect(2) call to /dev/shm/jack-1000/default/jack_0 failed (err=No such file or directory)
attempt to connect to server failed
Expression 'parameters->channelCount <= maxChans' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 1513
Expression 'ValidateParameters( outputParameters, hostApi, StreamDirection_Out )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 1845
Expression 'paInvalidSampleRate' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2043
Expression 'PaAlsaStreamComponent_InitialConfigure( &self->playback, outParams, self->primeBuffers, hwParamsPlayback, &realSr )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2717
Expression 'PaAlsaStream_Configure( stream, inputParameters, outputParameters, sampleRate, framesPerBuffer, &inputLatency, &outputLatency, &hostBufferSizeMode )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2838
wave_open_sound > Pa_OpenStream : err=-9997 (Invalid sample rate)
Expression 'paInvalidSampleRate' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2043
Expression 'PaAlsaStreamComponent_InitialConfigure( &self->playback, outParams, self->primeBuffers, hwParamsPlayback, &realSr )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2717
Expression 'PaAlsaStream_Configure( stream, inputParameters, outputParameters, sampleRate, framesPerBuffer, &inputLatency, &outputLatency, &hostBufferSizeMode )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2838
Expression 'paInvalidSampleRate' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2043
Expression 'PaAlsaStreamComponent_InitialConfigure( &self->playback, outParams, self->primeBuffers, hwParamsPlayback, &realSr )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2717
Expression 'PaAlsaStream_Configure( stream, inputParameters, outputParameters, sampleRate, framesPerBuffer, &inputLatency, &outputLatency, &hostBufferSizeMode )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2838
wave_open_sound > Pa_OpenStream : err=-9997 (Invalid sample rate)
Expression 'paInvalidSampleRate' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2043
Expression 'PaAlsaStreamComponent_InitialConfigure( &self->playback, outParams, self->primeBuffers, hwParamsPlayback, &realSr )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2717
Expression 'PaAlsaStream_Configure( stream, inputParameters, outputParameters, sampleRate, framesPerBuffer, &inputLatency, &outputLatency, &hostBufferSizeMode )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2838
Expression 'paInvalidSampleRate' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2043
Expression 'PaAlsaStreamComponent_InitialConfigure( &self->playback, outParams, self->primeBuffers, hwParamsPlayback, &realSr )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2717
Expression 'PaAlsaStream_Configure( stream, inputParameters, outputParameters, sampleRate, framesPerBuffer, &inputLatency, &outputLatency, &hostBufferSizeMode )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2838
wave_open_sound > Pa_OpenStream : err=-9997 (Invalid sample rate)
Expression 'paInvalidSampleRate' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2043
Expression 'PaAlsaStreamComponent_InitialConfigure( &self->playback, outParams, self->primeBuffers, hwParamsPlayback, &realSr )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2717
Expression 'PaAlsaStream_Configure( stream, inputParameters, outputParameters, sampleRate, framesPerBuffer, &inputLatency, &outputLatency, &hostBufferSizeMode )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2838
Expression 'paInvalidSampleRate' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2043
Expression 'PaAlsaStreamComponent_InitialConfigure( &self->playback, outParams, self->primeBuffers, hwParamsPlayback, &realSr )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2717
Expression 'PaAlsaStream_Configure( stream, inputParameters, outputParameters, sampleRate, framesPerBuffer, &inputLatency, &outputLatency, &hostBufferSizeMode )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2838
wave_open_sound > Pa_OpenStream : err=-9997 (Invalid sample rate)
Expression 'paInvalidSampleRate' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2043
Expression 'PaAlsaStreamComponent_InitialConfigure( &self->playback, outParams, self->primeBuffers, hwParamsPlayback, &realSr )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2717
Expression 'PaAlsaStream_Configure( stream, inputParameters, outputParameters, sampleRate, framesPerBuffer, &inputLatency, &outputLatency, &hostBufferSizeMode )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2838
there is no sound cant figure out whats wrong
Last edited by xabit (2014-11-19 04:31:10)

im glad that you wrote me moonswan,
lspci -v|grep -i snd
Kernel driver in use: snd_hda_intel
Kernel modules: snd_hda_intel
Kernel driver in use: snd_hda_intel
Kernel modules: snd_hda_intel
Kernel driver in use: snd_hda_intel
Kernel modules: snd_hda_intel
im on alsa alone, vlc and other prog. are working fine.
my system is fresh installed no fancy stuff installed, just wine for playing games.
wine sound works fine, but not together with non-wine application.
if i play games on wine i get on vlc:
Audio output failed:
The audio device "sysdefault:CARD=PCH" could not be used:
Device or resource busy.
i dont know if that has something to do with my problem with espeak
Last edited by xabit (2014-11-11 23:37:44)

How I can catch the word that was spoken in a string??

Hi
i'm doing a java aplication with speech recognition jsapi and i want know how i can convert tag form FinalRuleResult to string??
i want catch the word that was spoken in a string to evaluate the string in the sentences if
this is the code that i have developed:
public static void main(String[] args)
     {prueba inst = new prueba();
               inst.setVisible(true);
          try {
               RecognizerModeDesc descripcion = new RecognizerModeDesc(null, Boolean.TRUE);
               SpeechEngineChooser chooser = SpeechEngineChooser.getRecognizerDialog(descripcion);
               chooser.show();
               descripcion = chooser.getRecognizerModeDesc();
               reconocedor = Central.createRecognizer(descripcion);
               reconocedor.addEngineListener(new TestEngineListener());
               RecognizerAudioAdapter raud = new TestAudioListener();
               reconocedor.getAudioManager().addAudioListener(raud);
               reconocedor.allocate();
               reconocedor.waitEngineState(Recognizer.ALLOCATED);
               RuleSequence secuencia = new RuleSequence();
               RuleTag comando1 = new RuleTag(new RuleToken("vol"),"VOL");
               RuleTag comando2 = new RuleTag(new RuleToken("channel"),"CHANNEL");
               RuleTag comando3 = new RuleTag(new RuleToken("end"),"END");
               RuleTag comando4 = new RuleTag(new RuleToken("up"),"UP");
               RuleTag comando5 = new RuleTag(new RuleToken("down"),"DOWN");
               RuleAlternatives comandos = new RuleAlternatives();
               comandos.append(comando1);
               comandos.append(comando2);
               comandos.append(comando3);
               secuencia.append(comandos);
               RuleGrammar gramatica = reconocedor.newRuleGrammar("basepatrones");
               gramatica.setRule("testRule",secuencia,true);
               gramatica.setEnabled(true);
               reconocedor.suspend();
               reconocedor.commitChanges();
               reconocedor.waitEngineState(Recognizer.LISTENING);
               reconocedor.requestFocus();
               reconocedor.resume();
               reconocedor.addResultListener(new ResultAdapter() {
                    public void resultAccepted(final ResultEvent e)
                         try {
                              FinalRuleResult r = (FinalRuleResult)(e.getSource());
                              System.out.println("Obtenido el resultado "+r);
                              String tags[] = r.getTags();
if(tags == null) return;
                    //comparacion de :::
// in this point i want catch the word that was spoken in a string to evaluate the string in the sentences if
                              if(tags[0].equals("VOL"))
                                   JOptionPane.showMessageDialog(null,"has selecciuonado el volumen");
                                   jLabel1.setIcon(new ImageIcon(getClass().getClassLoader().getResource("control/controltv+.gif")));
                                   enviar("s");
                              if(tags[0].equals("CHANNEL"))
                                        JOptionPane.showMessageDialog(null,"QUIERES CAMBIAR CANAL???");
                                        jLabel1.setIcon(new ImageIcon(getClass().getClassLoader().getResource("control/controlt0.gif")));
                                        enviar("c");
                              if(tags[0].equals("END"))
                              JOptionPane.showMessageDialog(null,"SESION DE RECONOCIMIENTO TERMINADA");
                              jLabel1.setIcon(new ImageIcon(getClass().getClassLoader().getResource("control/controlt1.gif")));
                              System.exit(-1);
                              else return;
                         } catch(Exception e1) {}
          } catch (Exception e) {
               e.printStackTrace();
               System.exit(-1); }
     }

I donot know about Java Speech API.
But it is possible to recognize with Sphinx API.
you get it from [http://cmusphinx.sourceforge.net/sphinx4/]

Accessing file structure on hard disc

hello all,
this is regarding a e-learning project in flash
we have several course modules stored in individual folders
on the hard disc. each course module had it's individual xml file
which describes the module title,description, etc
at the root level i need to develop a main interface which at
runtime identifies the number of modules present (based on number
of folders)
opens each folder, finds the xml file and extracts the module
name and description
populate the list box in the main interface with module
name,a rollover would show the module descripton and on click would
open the relevant module
i am new to action script and do not know how to traverse
folders on action script. i stumbled across the JSAPI and the
newely added FLfile.dll but not sure if .jsfl can be used for this
project
thanks

In general, iTunes organizes according to tags, and does not consider the folder structure.
However, if you want to make a playlist of a single folder, there is an easy way. File > New Playlist. Give the playlist a name and open it. Drag the folder into it. (Try this will a small folder first so you can see how it works.)
Also, make sure to go into Edit > Preferences > Advanced, and make sure that "Keep..." and "Copy..." are both not checked. This will prevent iTunes from rearranging your files and folders.

How to insert API into NetBeans

Hello, i'm in the middle of doing my project using NetBeans as the platform. the problem is i don't know how to put JSAPI and JavaMail API package into my list of library in NetBeans.So, i hope somebody can give me a guide so that i can proceed with my project... thank you very much.

What exactly is your problem?
You cannot browse the necessary API using netbeans?
I don't use Netbeans, hence I am unable to answer this question. However, you can open the API using any browser (eg. IE, FF).
NB: This has nothing to do with Java Security Applications, APIs, and Issues. Actually, your question has nothing to do with Java. This is a Netbeans issue.

Steps to compile and deploy files on jsap

steps to compile and deploy files on jsap
classpath that has to be set
where to put the .class files
(Where to fnd JNDI tab)

jsas-sun java application Server
I like to depoy servlet files on this server
But it requires cloudscape to be started
(database server)
i have not even a single entry in the name of cloudscape

J2ME and JSAPI 2.0

Hi everyone,
How do i use JSAPI 2.0 in J2ME and if possible show me some examples.
Thanx in advance.

Currently JSAPI is not working well for j2me

Classpath Problem (Using JSAPI)

Hi,
I using IBM Via Voice as a the implementation of the JSAPI on my system. I've downloaded the speech for java pack from IBM Alphaworks and put it in the directory of
c:\ibmjs
This gives you access to the speech packages for utilisation in your programs so I should be able to import javax.speech in my programs. However the system doesn't see these classes.
Heres my Autoexec...
path=%path%;c:\jdk1.3.1_01\bin;c:\ibmjs\lib;
CLASSPATH=%CLASSPATH%;c:\ibmjs\lib\ibmjs.jar;
I presume the whole thing is just a classpath problem, does anybody have any idea from the above paths where I am going wrong?

i guess you have to put some of ibm's dll files coming with speech for java in the path (not classpath). it's not sufficient to have the directories in the path.
anyway, there come's an installation manual with speech for java which explaines all that.

JSAPI, speech output to file ???

Hi all,
I am not new to Java but using JSAPI first time, I have downloaded an example code which takes an Ascii string and speek accordingly, which can be hear on headphone. This code is working fine.
Now I would like to know that how can I get spoken output to a file, I mean I want to store voice to a file (WAV or any format) generated by the system.
Looking for your response,

you'll have a large amount of reading to be done, alot in the topic but
java provide an example program with source code.
there is audio recording capabilities in this. so once ya sort of the
audio capture you could add it as a method and record your
speech ouput.
http://java.sun.com/products/java-media/sound/samples/JavaSoundDemo/

JSAPI and MBROLA

Similar Messages

Maybe you are looking for