HRESULT TogglePause() //切换暂停
{
Paused = !Paused;
if (Paused)
return VoiceObj->Pause();
else
return VoiceObj->Resume();
}
void Speech::speechOutput(const char* str) {
ISpVoice* pVoice = NULL;
ISpObjectToken* cpAudioOutToken;
IEnumSpObjectTokens* cpEnum;
ULONG ulCount = 0;
if (FAILED(::CoInitialize(NULL)))
return;
HRESULT hr = CoCreateInstance(CLSID_SpVoice, NULL, CLSCTX_ALL, IID_ISpVoice, (void **)&pVoice);
if (SUCCEEDED (hr)) {
hr = SpEnumTokens( SPCAT_AUDIOOUT, NULL, NULL, &cpEnum);
}
if (SUCCEEDED (hr)) {
hr = cpEnum->GetCount( &ulCount);
}
while (SUCCEEDED(hr) && ulCount--) {
hr = cpEnum->Next( 1, &cpAudioOutToken, NULL );
wchar_t* deviceId = nullptr;
if(SUCCEEDED(hr)) {
hr = cpAudioOutToken->GetStringValue(L"DeviceId", &deviceId);
if(wcscmp(outputDevice, deviceId) == 0) break;
}
}
if (SUCCEEDED (hr)) {
hr = pVoice->SetOutput( cpAudioOutToken, TRUE );
}
if(SUCCEEDED(hr)) {
const size_t cSize = strlen(str)+1;
wchar_t* wc = new wchar_t[cSize];
size_t ret;
mbstowcs_s (&ret, wc, cSize, str, cSize);
hr = pVoice->Speak(wc, NULL, NULL);
pVoice->Release();
pVoice = NULL;
}
cpEnum->Release();
cpAudioOutToken->Release();
::CoUninitialize();
}
//请求指定语言的语音
bool SpBox::RequireLanguage(LPCWSTR langid)
{
IEnumSpObjectTokens* pEnum; //语音总选择
ISpObjectToken* pVoiceToken; //当前语音选择
ULONG ulCount = 0; //选择个数
WCHAR* pVoiceLang; //语音LangId
WCHAR* pVoiceText; //语音说明文字
HRESULT hr = SpEnumTokens(SPCAT_VOICES, NULL, NULL, &pEnum);
if (SUCCEEDED(hr))
{
hr = pEnum->GetCount(&ulCount);
}
while (SUCCEEDED(hr) && ulCount--){
if (SUCCEEDED(hr))
pEnum->Next(1, &pVoiceToken, 0);
if (SUCCEEDED(hr))
hr = SpGetLanguage(pVoiceToken, &pVoiceLang);
if (SUCCEEDED(hr) && !_wcsnicmp(pVoiceLang, langid, 3))
{
Token = pVoiceToken;
VoiceObj->SetVoice(Token);
SpGetDescription(Token, &pVoiceText, 0);
Description = pVoiceText;
return true;
}
}
return false;
}
HRESULT UnPause() //继续朗读
{
if (Paused)
{
Paused = false;
return VoiceObj->Resume();
}
return 0;
}
HRESULT Pause() //暂停朗读
{
if (!Paused)
{
Paused = true;
return VoiceObj->Pause();
}
return 0;
}
//------------------------------------------------------------------------------
bool SpeechApi51::isAvailable()
{
CoInitialize(NULL);
ISpVoice *sapi;
bool ret = true;
if (FAILED(CoCreateInstance(CLSID_SpVoice, NULL, CLSCTX_ALL, IID_ISpVoice, reinterpret_cast<void **>(&sapi))))
{
ret = false;
}
else
{
sapi->Release();
}
return ret;
}
int main(int argc, char* argv[])
{
ISpVoice * pVoice = NULL;
if (FAILED(::CoInitialize(NULL)))
return FALSE;
HRESULT hr = CoCreateInstance(CLSID_SpVoice, NULL, CLSCTX_ALL, IID_ISpVoice, (void **)&pVoice);
if (SUCCEEDED(hr))
{
hr = pVoice->Speak(L"Здравствуйте", 0, NULL);
// Change pitch
hr = pVoice->Speak(L"Вы меня <pitch middle = '-10'/> слышите?", SPF_IS_XML, NULL);
pVoice->Release();
pVoice = NULL;
}
::CoUninitialize();
return TRUE;
}
bool TextToSpeech::say(string wordToSay)
{
//convert string to wstring to use with speech function
wstring wstr(wordToSay.begin(), wordToSay.end());
ISpVoice * pVoice = NULL;
if (FAILED(::CoInitialize(NULL)))
return FALSE;
HRESULT hr = CoCreateInstance(CLSID_SpVoice, NULL, CLSCTX_ALL, IID_ISpVoice, (void **)&pVoice);
if (SUCCEEDED(hr))
{
long rate = -5;
pVoice->SetRate(rate);
hr = pVoice->Speak(wstr.c_str(), 0, NULL);
pVoice->Release();
pVoice = NULL;
}
::CoUninitialize();
return TRUE;
}
int main(int argc, char* argv[])
{
ISpVoice * pVoice = NULL;
if (FAILED(::CoInitialize(NULL)))
return FALSE;
HRESULT hr = CoCreateInstance(CLSID_SpVoice, NULL, CLSCTX_ALL, IID_ISpVoice, (void **)&pVoice);
if (SUCCEEDED(hr))
{
//hr = pVoice->Speak(L"Hello Brad <pitch middle = '-10'/> gwaps", SPF_IS_XML, NULL);
hr = pVoice->Speak(L"Myca needs vog", 0, NULL);
//hr = pVoice->Speak(L"cliff golem tashed", 0, NULL);
//hr = pVoice->Speak(L"Invis failing, invis failing", 0, NULL);
//hr = pVoice->Speak(L"charm break, <pitch middle = '-10'/> beat down imminent", SPF_IS_XML, NULL);
hr = pVoice->Speak(L"pet is loose, <pitch middle = '+10'/> pet is loose", 8, NULL);
pVoice->Release();
pVoice = NULL;
}
::CoUninitialize();
return TRUE;
}
/**********************************************************************
* CTextRun::Speak *
*-----------------*
* Description:
* Speaks the text associated with this CTextRun using TTS.
*
* Return:
* S_OK
* Return value of ITextRange::GetText()
* Return value of ISpVoice::Speak()
**********************************************************************/
HRESULT CTextRun::Speak( ISpVoice &rVoice )
{
_ASSERTE( m_cpTextRange );
if ( !m_cpTextRange )
{
return E_UNEXPECTED;
}
// Get the text and speak it.
BSTR bstrText;
HRESULT hr = m_cpTextRange->GetText( &bstrText );
if( SUCCEEDED( hr ) )
{
hr = rVoice.Speak( bstrText, SPF_ASYNC, NULL );
::SysFreeString( bstrText );
}
return hr;
} /* CTextRun::Speak */
HRESULT Speak() //开始朗读
{
UnPause();
return VoiceObj->Speak(Text.c_str(), Flags, 0);
}
ULONG GetStatus() //返回当前语音状态: 0完毕;SPRS_IS_SPEAKING 正在处理
{
VoiceObj->GetStatus(&Status, 0);
return Status.dwRunningState;
}
int main(int argc, char **argv)
{
ISpVoice *pVoice = NULL;
WCHAR line_buffer[LINE_LENGTH];
bool exitflag = FALSE;
int counter = 0;
if (FAILED(::CoInitialize(NULL)))
{
printf("ERROR: Couldn't initialise COM.\n");
return FALSE;
}
HRESULT hr = CoCreateInstance(CLSID_SpVoice, NULL, CLSCTX_ALL, IID_ISpVoice, (void **)&pVoice);
if( SUCCEEDED( hr ) )
{
// For some reason, if you don't do this, speech cuts out
// (only on first announcement)...
pVoice->Speak(L" ", SPF_IS_NOT_XML, NULL);
// Main loop...
while( ! exitflag )
{
for(counter = 0; counter < LINE_LENGTH; counter++ )
{
// Fill up the buffer...
line_buffer[counter] = getwchar();
// Check for exit condition...
if( line_buffer[counter] == WEOF )
{
line_buffer[counter] = 0;
exitflag = TRUE;
break;
}
// Break at end of line...
if( line_buffer[counter] == L'\n' )
{
line_buffer[counter] = 0;
break;
}
}
counter = 0;
// Should the synth's UI be displayed?
if ( line_buffer == L"DisplayUI" )
{
int supported = 0;
hr = pVoice->IsUISupported(SPDUI_EngineProperties, NULL, NULL, &supported);
if( SUCCEEDED( hr ) && supported )
{
hr = pVoice->DisplayUI(NULL, NULL, SPDUI_EngineProperties, NULL, NULL);
if( ! SUCCEEDED( hr ) )
{
pVoice->Speak(L"There was an error displaying the properties window.\n", SPF_IS_NOT_XML|SPF_ASYNC|SPF_PURGEBEFORESPEAK, NULL);
}
}
else
{
pVoice->Speak(L"Your current voice doesn't support a properties window.\n", SPF_IS_NOT_XML|SPF_ASYNC|SPF_PURGEBEFORESPEAK, NULL);
}
}
// Was the message high-priority?
if( line_buffer[0] == L'!' )
{
line_buffer[0] = L' ';
pVoice->Speak(line_buffer, SPF_IS_NOT_XML|SPF_ASYNC|SPF_PURGEBEFORESPEAK, NULL);
}
else
{
pVoice->Speak(line_buffer, SPF_IS_NOT_XML|SPF_ASYNC, NULL);
}
}
// Allow the user to hear the rest of the speech buffer...
pVoice->Speak(L" ", SPF_IS_NOT_XML, NULL);
pVoice->Release();
pVoice = NULL;
}
else
{
printf("ERROR: Couldn't initialise SAPI 5.1.\n");
}
::CoUninitialize();
return TRUE;
}
HRESULT Speak(LPCWSTR pwcs)
{
UnPause();
return VoiceObj->Speak(pwcs, Flags, 0);
}
void TextToSpeechPrivate::setVolume(int volume) {
if (pVoice)
pVoice->SetVolume(volume);
}
void TextToSpeechPrivate::say(const QString &text) {
if (pVoice) {
pVoice->Speak((const wchar_t *) text.utf16(), SPF_ASYNC, NULL);
}
}
void Sound::test() {
ISpVoice * pVoice = NULL;
ISpObjectToken* pVoiceToken=nullptr;
IEnumSpObjectTokens* pEnum;
ULONG ulCount = 0;
if (FAILED(::CoInitialize(NULL)))
{
return;
}
HRESULT hr = S_OK;
// Find the best matching installed en-us recognizer.
CComPtr<ISpObjectToken> cpRecognizerToken;
if (SUCCEEDED(hr))
{
hr = SpFindBestToken(SPCAT_RECOGNIZERS, L"language=409", NULL, &cpRecognizerToken);
}
// Create the in-process recognizer and immediately set its state to inactive.
CComPtr<ISpRecognizer> cpRecognizer;
if (SUCCEEDED(hr))
{
hr = cpRecognizer.CoCreateInstance(CLSID_SpInprocRecognizer);
}
if (SUCCEEDED(hr))
{
hr = cpRecognizer->SetRecognizer(cpRecognizerToken);
}
if (SUCCEEDED(hr))
{
hr = cpRecognizer->SetRecoState(SPRST_INACTIVE);
}
// Create a new recognition context from the recognizer.
CComPtr<ISpRecoContext> cpContext;
if (SUCCEEDED(hr))
{
hr = cpRecognizer->CreateRecoContext(&cpContext);
}
// Subscribe to the speech recognition event and end stream event.
if (SUCCEEDED(hr))
{
ULONGLONG ullEventInterest = SPFEI(SPEI_RECOGNITION);
hr = cpContext->SetInterest(ullEventInterest, ullEventInterest);
}
// Establish a Win32 event to signal when speech events are available.
HANDLE hSpeechNotifyEvent = INVALID_HANDLE_VALUE;
if (SUCCEEDED(hr))
{
hr = cpContext->SetNotifyWin32Event();
}
if (SUCCEEDED(hr))
{
hSpeechNotifyEvent = cpContext->GetNotifyEventHandle();
if (INVALID_HANDLE_VALUE == hSpeechNotifyEvent)
{
// Notification handle unsupported.
hr = E_NOINTERFACE;
}
}
// Initialize an audio object to use the default audio input of the system and set the recognizer to use it.
CComPtr<ISpAudio> cpAudioIn;
if (SUCCEEDED(hr))
{
hr = cpAudioIn.CoCreateInstance(CLSID_SpMMAudioIn);
}
if (SUCCEEDED(hr))
{
hr = cpRecognizer->SetInput(cpAudioIn, TRUE);
}
// Populate a WAVEFORMATEX struct with our desired output audio format. information.
WAVEFORMATEX* pWfexCoMemRetainedAudioFormat = NULL;
GUID guidRetainedAudioFormat = GUID_NULL;
if (SUCCEEDED(hr))
{
hr = SpConvertStreamFormatEnum(SPSF_16kHz16BitMono, &guidRetainedAudioFormat, &pWfexCoMemRetainedAudioFormat);
}
// Instruct the recognizer to retain the audio from its recognition results.
if (SUCCEEDED(hr))
{
hr = cpContext->SetAudioOptions(SPAO_RETAIN_AUDIO, &guidRetainedAudioFormat, pWfexCoMemRetainedAudioFormat);
}
if (NULL != pWfexCoMemRetainedAudioFormat)
{
CoTaskMemFree(pWfexCoMemRetainedAudioFormat);
}
// Create a new grammar and load an SRGS grammar from file.
CComPtr<ISpRecoGrammar> cpGrammar;
if (SUCCEEDED(hr))
{
hr = cpContext->CreateGrammar(0, &cpGrammar);
}
if (SUCCEEDED(hr))
{
hr = cpGrammar->LoadCmdFromFile(L"grammar.grxml", SPLO_STATIC);
}
// Set all top-level rules in the new grammar to the active state.
if (SUCCEEDED(hr))
{
hr = cpGrammar->SetRuleState(NULL, NULL, SPRS_ACTIVE);
}
// Set the recognizer state to active to begin recognition.
if (SUCCEEDED(hr))
{
hr = cpRecognizer->SetRecoState(SPRST_ACTIVE_ALWAYS);
}
// Establish a separate Win32 event to signal the event loop exit.
HANDLE hExitEvent = CreateEventW(NULL, FALSE, FALSE, NULL);
// Collect the events listened for to pump the speech event loop.
HANDLE rghEvents[] = { hSpeechNotifyEvent, hExitEvent };
// Speech recognition event loop.
BOOL fContinue = TRUE;
while (fContinue && SUCCEEDED(hr))
{
// Wait for either a speech event or an exit event, with a 15 second timeout.
DWORD dwMessage = WaitForMultipleObjects(sp_countof(rghEvents), rghEvents, FALSE, 15000);
switch (dwMessage)
{
// With the WaitForMultipleObjects call above, WAIT_OBJECT_0 is a speech event from hSpeechNotifyEvent.
case WAIT_OBJECT_0:
{
// Sequentially grab the available speech events from the speech event queue.
CSpEvent spevent;
while (S_OK == spevent.GetFrom(cpContext))
{
switch (spevent.eEventId)
{
case SPEI_RECOGNITION:
{
// Retrieve the recognition result and output the text of that result.
ISpRecoResult* pResult = spevent.RecoResult();
LPWSTR pszCoMemResultText = NULL;
hr = pResult->GetText(SP_GETWHOLEPHRASE, SP_GETWHOLEPHRASE, TRUE, &pszCoMemResultText, NULL);
if (SUCCEEDED(hr))
{
wprintf(L"Recognition event received, text=\"%s\"\r\n", pszCoMemResultText);
}
// Also retrieve the retained audio we requested.
CComPtr<ISpStreamFormat> cpRetainedAudio;
if (SUCCEEDED(hr))
{
hr = pResult->GetAudio(0, 0, &cpRetainedAudio);
}
// To demonstrate, we'll speak the retained audio back using ISpVoice.
CComPtr<ISpVoice> cpVoice;
if (SUCCEEDED(hr))
{
hr = cpVoice.CoCreateInstance(CLSID_SpVoice);
}
if (SUCCEEDED(hr))
{
hr = cpVoice->SpeakStream(cpRetainedAudio, SPF_DEFAULT, 0);
}
if (NULL != pszCoMemResultText)
{
CoTaskMemFree(pszCoMemResultText);
}
break;
}
}
}
break;
}
case WAIT_OBJECT_0 + 1:
case WAIT_TIMEOUT:
{
// Exit event or timeout; discontinue the speech loop.
fContinue = FALSE;
//break;
}
}
}
CoUninitialize();
CComPtr <ISpVoice> cpVoice;
CComPtr <ISpStream> cpStream;
CSpStreamFormat cAudioFmt;
//Create a SAPI Voice
hr = cpVoice.CoCreateInstance(CLSID_SpVoice);
//Set the audio format
if (SUCCEEDED(hr))
{
hr = cAudioFmt.AssignFormat(SPSF_22kHz16BitMono);
}
//Call SPBindToFile, a SAPI helper method, to bind the audio stream to the file
if (SUCCEEDED(hr))
{
hr = SPBindToFile(L"c:\\ttstemp.wav", SPFM_CREATE_ALWAYS,
&cpStream, &cAudioFmt.FormatId(), cAudioFmt.WaveFormatExPtr());
}
//set the output to cpStream so that the output audio data will be stored in cpStream
if (SUCCEEDED(hr))
{
hr = cpVoice->SetOutput(cpStream, TRUE);
}
//Speak the text "hello world" synchronously
if (SUCCEEDED(hr))
{
hr = cpVoice->Speak(L"Hello World", SPF_DEFAULT, NULL);
}
//close the stream
if (SUCCEEDED(hr))
{
hr = cpStream->Close();
}
//Release the stream and voice object
cpStream.Release();
cpVoice.Release();
CComPtr<ISpGrammarBuilder> cpGrammarBuilder;
SPSTATEHANDLE hStateTravel;
// Create (if rule does not already exist)
// top-level Rule, defaulting to Active.
hr = cpGrammarBuilder->GetRule(L"Travel", 0, SPRAF_TopLevel | SPRAF_Active, TRUE, &hStateTravel);
// Approach 1: List all possible phrases.
// This is the most intuitive approach, and it does not sacrifice efficiency
// because the grammar builder will merge shared sub-phrases when possible.
// There is only one root state, hStateTravel, and the terminal NULL state,
// and there are six unique transitions between root state and NULL state.
/* XML Approximation:
<rule id="Travel">
<item> fly to Seattle </item>
<item> fly to New York </item>
<item> fly to Washington DC </item>
<item> drive to Seattle </item>
<item> drive to New York </item>
<item> drive to Washington DC </item>
</rule>
*/
// Create set of peer phrases, each containing complete phrase.
// Note: the word delimiter is set as " ", so that the text we
// attach to the transition can be multiple words (for example,
// "fly to Seattle" is implicitly "fly" + "to" + "Seattle"):
if (SUCCEEDED(hr))
{
hr = cpGrammarBuilder->AddWordTransition(hStateTravel, NULL, L"fly to Seattle", L" ", SPWT_LEXICAL, 1, NULL);
}
if (SUCCEEDED(hr))
{
hr = cpGrammarBuilder->AddWordTransition(hStateTravel, NULL, L"fly to New York", L" ", SPWT_LEXICAL, 1, NULL);
}
if (SUCCEEDED(hr))
{
hr = cpGrammarBuilder->AddWordTransition(hStateTravel, NULL, L"fly to Washington DC", L" ", SPWT_LEXICAL, 1, NULL);
}
if (SUCCEEDED(hr))
{
hr = cpGrammarBuilder->AddWordTransition(hStateTravel, NULL, L"drive to Seattle", L" ", SPWT_LEXICAL, 1, NULL);
}
if (SUCCEEDED(hr))
{
hr = cpGrammarBuilder->AddWordTransition(hStateTravel, NULL, L"drive to New York", L" ", SPWT_LEXICAL, 1, NULL);
}
if (SUCCEEDED(hr))
{
hr = cpGrammarBuilder->AddWordTransition(hStateTravel, NULL, L"drive to Washington DC", L" ", SPWT_LEXICAL, 1, NULL);
}
// Find the best matching installed en-US recognizer.
//CComPtr<ISpObjectToken> cpRecognizerToken;
if (SUCCEEDED(hr))
{
hr = SpFindBestToken(SPCAT_RECOGNIZERS, L"language=409", NULL, &cpRecognizerToken);
}
// Create the in-process recognizer and immediately set its state to inactive.
//CComPtr<ISpRecognizer> cpRecognizer;
if (SUCCEEDED(hr))
{
hr = cpRecognizer.CoCreateInstance(CLSID_SpInprocRecognizer);
}
if (SUCCEEDED(hr))
{
hr = cpRecognizer->SetRecognizer(cpRecognizerToken);
}
if (SUCCEEDED(hr))
{
hr = cpRecognizer->SetRecoState(SPRST_INACTIVE);
}
// Create a new recognition context from the recognizer.
//CComPtr<ISpRecoContext> cpContext;
if (SUCCEEDED(hr))
{
hr = cpRecognizer->CreateRecoContext(&cpContext);
}
// Subscribe to the speech recognition event and end stream event.
if (SUCCEEDED(hr))
{
ULONGLONG ullEventInterest = SPFEI(SPEI_RECOGNITION) | SPFEI(SPEI_END_SR_STREAM);
hr = cpContext->SetInterest(ullEventInterest, ullEventInterest);
}
// Establish a Win32 event to signal when speech events are available.
//HANDLE hSpeechNotifyEvent = INVALID_HANDLE_VALUE;
if (SUCCEEDED(hr))
{
hr = cpContext->SetNotifyWin32Event();
}
if (SUCCEEDED(hr))
{
hr = cpContext->SetNotifyWin32Event();
}
if (SUCCEEDED(hr))
{
hSpeechNotifyEvent = cpContext->GetNotifyEventHandle();
if (INVALID_HANDLE_VALUE == hSpeechNotifyEvent)
{
// Notification handle unsupported
//hr = SPERR_UNITIALIZED;
}
}
// Set up an audio input stream using a .wav file and set the recognizer's input.
CComPtr<ISpStream> cpInputStream;
if (SUCCEEDED(hr))
{
hr = SPBindToFile(L"Test.wav", SPFM_OPEN_READONLY, &cpInputStream);
}
if (SUCCEEDED(hr))
{
hr = cpRecognizer->SetInput(cpInputStream, TRUE);
}
// Create a new grammar and load an SRGS grammar from file.
//CComPtr<ISpRecoGrammar> cpGrammar;
if (SUCCEEDED(hr))
{
hr = cpContext->CreateGrammar(0, &cpGrammar);
}
if (SUCCEEDED(hr))
{
hr = cpGrammar->LoadCmdFromFile(L"grammar.grxml", SPLO_STATIC);
}
// Set all top-level rules in the new grammar to the active state.
if (SUCCEEDED(hr))
{
hr = cpGrammar->SetRuleState(NULL, NULL, SPRS_ACTIVE);
}
// Finally, set the recognizer state to active to begin recognition.
if (SUCCEEDED(hr))
{
hr = cpRecognizer->SetRecoState(SPRST_ACTIVE_ALWAYS);
}
hr = CoCreateInstance(CLSID_SpVoice, NULL, CLSCTX_ALL, IID_ISpVoice, (void **)&pVoice);
if (SUCCEEDED(hr)) {
hr = SpEnumTokens(SPCAT_VOICES, L"Gender=Female", NULL, &pEnum);
if (SUCCEEDED(hr))
{
// Get the number of voices.
hr = pEnum->GetCount(&ulCount);
}
// Obtain a list of available voice tokens, set
// the voice to the token, and call Speak.
while (SUCCEEDED(hr) && ulCount--) {
if (pVoiceToken != nullptr) {
pVoiceToken->Release();
}
if (SUCCEEDED(hr))
{
hr = pEnum->Next(1, &pVoiceToken, NULL);
}
if (SUCCEEDED(hr))
{
hr = pVoice->SetVoice(pVoiceToken);
}
if (SUCCEEDED(hr))
{
wchar_t* start = L"<?xml version=\"1.0\" encoding=\"ISO - 8859 - 1\"?><speak version = \"1.0\" xmlns = \"http://www.w3.org/2001/10/synthesis\" xml:lang = \"en-US\">";
wchar_t* end = L"</speak>";
const wchar_t *xml = L"<voice required = \"Gender=Male\"> hi! <prosody pitch=\"fast\"> This is low pitch. </prosody><prosody volume=\"x - loud\"> This is extra loud volume. </prosody>";
wstring s = start;
s += xml;
s += end;
hr = pVoice->Speak(xml, SPF_IS_XML| SPF_ASYNC, 0);
//hr = pVoice->Speak(L"How are you?", SPF_DEFAULT, NULL);
}
}
/*
if (SUCCEEDED(hr)) {
hr = pEnum->Next(1, &pVoiceToken, NULL);
if (SUCCEEDED(hr)) {
hr = pVoice->SetVoice(pVoiceToken);
// Set the output to the default audio device.
if (SUCCEEDED(hr)) {
hr = pVoice->SetOutput(NULL, TRUE);
if (SUCCEEDED(hr)) {
hr = pVoice->Speak(L"Hello, world!", SPF_DEFAULT, 0);
}
}
}
}
*/
pVoice->Release();
}
::CoUninitialize();
}
HRESULT SetVolume(USHORT usVolume) //设置音量（朗读开始前有效）
{
return VoiceObj->SetVolume(usVolume);
}
HRESULT SetRate(long RateAdjust) //设置语速（同上）
{
return VoiceObj->SetRate(RateAdjust);
}
bool speak(wchar_t * text, wchar_t * pszReqAttribs)
{
ISpVoice * pVoice = NULL;
HRESULT stInitializing = CoCreateInstance(CLSID_SpVoice, NULL, CLSCTX_ALL, IID_ISpVoice, (void **)&pVoice);
if (SUCCEEDED(stInitializing))
{
ISpObjectToken* cpToken(NULL);
HRESULT stTokenFinding = SpFindBestToken(SPCAT_VOICES, pszReqAttribs, L"", &cpToken);
if (SUCCEEDED(stTokenFinding))
{
HRESULT stVoiceSetting = pVoice->SetVoice(cpToken);
if (SUCCEEDED(stVoiceSetting))
{
HRESULT stSpoken = pVoice->Speak(text, 0, NULL);
if (SUCCEEDED(stSpoken))
{
cpToken->Release();
cpToken = NULL;
pVoice->Release();
pVoice = NULL;
return true;
}
else
{
cpToken->Release();
cpToken = NULL;
pVoice->Release();
pVoice = NULL;
wcout << "Error, I couldn't play this text " << text << endl;
return false;
}
}
else
{
cpToken->Release();
cpToken = NULL;
pVoice->Release();
pVoice = NULL;
wcout << "Error, I can't set this voice " << pszReqAttribs << endl;
return false;
}
}
else
{
pVoice->Release();
pVoice = NULL;
wcout << "Error, I can't find this voice " << pszReqAttribs << endl;
return false;
}
}
else {
wcout << "Error, I can't create Voice instance" << endl;
return false;
}
}
int main(int argc, char* argv[])
{
Arguments arguments(argc, argv);
//Initialize Pocketsphinx
mic_data_t mic;
continuous_init(arguments, mic);
//Initialize Voice
ISpVoice * pVoice = NULL;
if (FAILED(::CoInitialize(NULL)))
return FALSE;
HRESULT hr = CoCreateInstance(CLSID_SpVoice, NULL, CLSCTX_ALL, IID_ISpVoice, (void **)&pVoice);
if (SUCCEEDED(hr))
std::cout << "Speech Initialized" << std::endl;
//Initialize Rebecca
AimlFacade aiml;
GraphBuilder &builder = aiml.getGraphBuilder();
myCallBacks callback;
builder.setCallBacks(&callback);
rebecca_init(arguments, builder);
//Main code
try
{
/*
* Send a initial conversation of "connect" to
* annotated alice and get the response.
*/
StringPimpl response = builder.getResponse("connect");
/*
* Get the botName which should be Rebecca since that is
* the name give in the configuration file properties.xml
* which we parsed above.
*/
string botName = builder.getBotPredicate("name").c_str();
//Send the initial opening line of the bot
cout << botName << " says: " << response.c_str() << endl;
hr = pVoice->Speak(s2ws(response.c_str()).c_str(), 0, NULL);
pVoice->WaitUntilDone(15000);
/*
* The main loop to get the input
* from the user until the user types '/exit'
*/
while (true)
{
//getUtterance(mic);
//string input = string(mic.hyp);
string input;
getline(cin, input);
if (input == "/exit" || input == "GOOD NIGHT")
{
/*
* The user wants to exit so break
* out of the while(true) loop
*/
continuous_exit(mic);
pVoice->Release();
pVoice = NULL;
::CoUninitialize();
break;
}
else //The user gave an input to the bot
{
//Here we get some internal Rebecca information.
cout << endl
<< "Internal information:" << endl
<< "=====================" << endl
<< input << " : "
<< builder.getThat().c_str() << " : "
<< builder.getTopic().c_str() << endl;
/*
* Ahhh finally. We give the user input to Rebecca Aiml's loaded
* AIML and get the response back.
*/
StringPimpl response = builder.getResponse(input.c_str());
cout << "=====================" << endl << endl;
//Print out what Rebecca says.
cout << botName << " says: " << response.c_str() << endl;
hr = pVoice->Speak(s2ws(response.c_str()).c_str(), 0, NULL);
pVoice->WaitUntilDone(15000);
}
}
}
catch (Exception &e)
{
cout << "[An unknown exception occured, Terminating program]" << endl;
cout << "[" << e.what() << "]";
return 1;
}
//Everything smooth. Exit normally.
return 0;
}
