record_audio.py 文件源码

def listen_for_speech(threshold=THRESHOLD, num_phrases=1):
    """
    Listens to Microphone, extracts phrases from it and sends it to
    Google's TTS service and returns response. a "phrase" is sound
    surrounded by silence (according to threshold). num_phrases controls
    how many phrases to process before finishing the listening process
    (-1 for infinite).
    """

    #Open stream
    p = pyaudio.PyAudio()

    stream = p.open(format=FORMAT,
                    channels=CHANNELS,
                    rate=RATE,
                    input=True,
                    frames_per_buffer=CHUNK)

    print "* Listening mic. "
    audio2send = []
    cur_data = ''  # current chunk  of audio data
    rel = RATE/CHUNK
    slid_win = deque(maxlen=SILENCE_LIMIT * rel)
    #Prepend audio from 0.5 seconds before noise was detected
    prev_audio = deque(maxlen=PREV_AUDIO * rel)
    started = False
    n = num_phrases
    response = []
    while (num_phrases == -1 or n > 0):
        cur_data = stream.read(CHUNK)
        slid_win.append(math.sqrt(abs(audioop.avg(cur_data, 4))))
        if(sum([x > THRESHOLD for x in slid_win]) > 0):
            if(not started):
                print "Starting record of phrase"
                started = True
            audio2send.append(cur_data)
        elif (started is True):
            print "Finished"
            # The limit was reached, finish capture and deliver.
            filename = save_speech(list(prev_audio) + audio2send, p)
            result = transcribe_audio('speech.wav')
            print result
            text = result['data']
            print("Text: " + text + "\n")
            started = False
            slid_win = deque(maxlen=SILENCE_LIMIT * rel)
            prev_audio = deque(maxlen=0.5 * rel)
            audio2send = []
            n -= 1
    print "* Done recording"
    stream.close()
    p.terminate()