Introduction

import pyaudioimport numpy as npimport whisper
# Initialize Whisper modelmodel = whisper.load_model("base")  # Options: "tiny", "base", "small", "medium", "large"
# PyAudio settingschunk = 1024  # Size of audio blockformat = pyaudio.paInt16  # Audio formatchannels = 1  # Mono channelrate = 16000  # Sample rate
p = pyaudio.PyAudio()
# Open audio streamstream = p.open(format=format,                channels=channels,                rate=rate,                input=True,                frames_per_buffer=chunk)
print("Starting real-time speech recognition...")
try:    while True:        # Read audio data        data = stream.read(chunk)        audio_data = np.frombuffer(data, dtype=np.int16)
        # Convert audio data to format required by Whisper        audio_float = audio_data.astype(np.float32) / 32768.0  # Normalize to [-1, 1]        audio_float = np.pad(audio_float, (0, 16000 - len(audio_float)), 'constant')  # Pad to 16 seconds
        # Perform speech recognition        result = model.transcribe(audio_float, fp16=False)  # fp16=False to avoid issues on some hardware        print("Recognition result:", result['text'])
except KeyboardInterrupt:    print("Stopping speech recognition.")
finally:    # Close audio stream    stream.stop_stream()    stream.close()    p.terminate()

# This example requires environment variables named "SPEECH_KEY" and "SPEECH_REGION"speech_config = speechsdk.SpeechConfig(subscription='xxx', region='eastasia')speech_config.speech_recognition_language="zh-CN"
audio_config = speechsdk.audio.AudioConfig(use_default_microphone=True)speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)
print("Speak into your microphone.")
def stop_cb(evt):    print('CLOSING on {}'.format(evt))    speech_recognizer.stop_continuous_recognition()    global done    done = True
def sent_to_model(text):        response = get_response(text)    if response:        print("model response:",response)        text_to_speech(response)    
#speech_recognizer.recognizing.connect(lambda evt: print('RECOGNIZING: {}'.format(evt)))speech_recognizer.recognized.connect(lambda evt: print('RECOGNIZED: {}'.format(evt)) or sent_to_model(evt.result.text))speech_recognizer.session_started.connect(lambda evt: print('SESSION STARTED: {}'.format(evt)))speech_recognizer.session_stopped.connect(lambda evt: print('SESSION STOPPED {}'.format(evt)))speech_recognizer.canceled.connect(lambda evt: print('CANCELED {}'.format(evt)))
speech_recognizer.session_stopped.connect(stop_cb)speech_recognizer.canceled.connect(stop_cb)
speech_recognizer.start_continuous_recognition()while not done:    time.sleep(.5)

import appbuilderimport os
os.environ['APPBUILDER_TOKEN'] = "xxxxxxxxxxxxxxxxxxxxxxxxxxx"app_id = "acf19b27-1019-45fb-b163-a454d31ef014"def agent_query( query: str):
    # Initialize Agent instance    agent = appbuilder.AppBuilderClient(app_id)    # Create conversation ID    conversation_id = agent.create_conversation()    print("Your AppBuilder App ID is: {}".format(app_id))    print("processing")
    response_message = agent.run(conversation_id=conversation_id, query=query)    description = response_message.content.answer
    return description

if __name__ == '__main__':    prompt = 'Tell a story about Cinderella'    print(agent_query(prompt))

async def text_to_speech(text):    speech_config2 = speechsdk.SpeechConfig(subscription='xxx', region='eastasia')    audio_config2 = speechsdk.audio.AudioOutputConfig(use_default_speaker=True)
    # The neural multilingual voice can speak different languages based on the input text.    speech_config2.speech_synthesis_voice_name='zh-CN-XiaoyiNeural'    speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=speech_config2, audio_config=audio_config2)
    # Get text from the console and synthesize to the default speaker.        print("tts=>>>",text)    speech_synthesis_result = speech_synthesizer.speak_text_async(text).get()
    if speech_synthesis_result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:        print("Speech synthesized for text [{}]".format(text))    elif speech_synthesis_result.reason == speechsdk.ResultReason.Canceled:        cancellation_details = speech_synthesis_result.cancellation_details        print("Speech synthesis canceled: {}".format(cancellation_details.reason))        if cancellation_details.reason == speechsdk.CancellationReason.Error:            if cancellation_details.error_details:                print("Error details: {}".format(cancellation_details.error_details))                print("Did you set the speech resource key and region values?")