使用pyAudio錄音及播放

pyAudio是開源聲音庫PortAudio(http://www.portaudio.com/)提供的Python庫

使用pyAudio播放聲音

import pyaudio
import wave

buf = 1024

wf = wave.open(r"C:\Users\yuli\Desktop\a\forest.wav", 'rb')

p = pyaudio.PyAudio()

stream = p.open(format = p.get_format_from_width(wf.getsampwidth()),
                channels = wf.getnchannels(),
                rate = wf.getframerate(),
                output = True)

while True:
    data = wf.readframes(buf)
    if data == "": break
    stream.write(data)

stream.close()
p.terminate()

pyAudio類的open函數參數:

• rate - 取樣頻率
• channel - 聲道
• 1=>mono為單聲道
• 2=>stereo為雙聲道(立體聲)
• format - 取樣值量化格式
• pyaudio.paFloat32 = 1
• pyaudio.paInt32 = 2
• pyaudio.paInt24 = 4
• pyaudio.paInt16 = 8
• pyaudio.paInt8 = 16
• pyaudio.paUInt8 = 32
• pyaudio.paCustomFormat = 65536
• input - 若為True則為開啟輸入流
• output - 若為True則為開啟輸出流
• input_device_index - 輸入所使用的設備編號，不指定則為系統預設
• output_device_index - 輸出所使用的設備編號，不指定則為系統預設
• frames_per_buffer - 緩存塊大小
• start - 是否立即開始輸入輸出流，不指定則為True

使用pyAudio錄音

from pyaudio import PyAudio, paInt16 
import numpy as np 
from datetime import datetime 
import wave 

def save_wave_file(filename, data): 
    wf = wave.open(filename, 'wb') 
    wf.setnchannels(1) 
    wf.setsampwidth(2) 
    wf.setframerate(SAMPLING_RATE) 
    wf.writeframes(b"".join(data)) 
    wf.close() 

NUM_SAMPLES = 2000      
SAMPLING_RATE = 8000    
LEVEL = 1500            
COUNT_NUM = 20          
SAVE_LENGTH = 8         

pa = PyAudio() 
stream = pa.open(format=paInt16, channels=1, rate=SAMPLING_RATE, input=True, 
                frames_per_buffer=NUM_SAMPLES) 

save_count = 0 
save_buffer = [] 

while True: 
    string_audio_data = stream.read(NUM_SAMPLES) 
    audio_data = np.fromstring(string_audio_data, dtype=np.short) 
    large_sample_count = np.sum( audio_data > LEVEL ) 
    print(np.max(audio_data))
    if large_sample_count > COUNT_NUM: 
        save_count = SAVE_LENGTH 
    else: 
        save_count -= 1 

    if save_count < 0: 
        save_count = 0 

    if save_count > 0: 
        save_buffer.append( string_audio_data ) 
    else: 
        if len(save_buffer) > 0: 
            filename = datetime.now().strftime("%Y-%m-%d_%H_%M_%S") + ".wav" 
            save_wave_file(filename, save_buffer) 
            save_buffer = [] 
            print(filename, "saved")