python 声音

环境：python3.6.3 pyaudio

基础知识：

声音在电子设备里的存储形式：在某一时间点的数值大小（0-255）
采样率：每秒采集的次数
采样格式：每次采集获取的位数
块（chunk)：wave格式的文件格式

播放

# 播放
import wave,pyaudio

wf=wave.open("ok.wav","rb")

p=pyaudio.PyAudio()

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

data=wf.readframes(102)
while data !=" ":
    stream.write(data)
    data=wf.readframes(102)

stream.stop_stream()
stream.close()

p.terminate()

录音并保存

# 录音并保存
# MPG123 免费的命令行MP3播放器

import pyaudio
import wave

CHUNK = 1024 # 块大小
FORMAT = pyaudio.paInt16 # 每次采集的位数
CHANNELS = 2 # 声道数
RATE = 44100 # 采样率：每秒采集数据的次数
RECORD_SECONDS = 5 # 录音时间
WAVE_OUTPUT_FILENAME = "output.wav" # 文件存放位置

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

print("* recording")

frames = []

for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
    data = stream.read(CHUNK)
    frames.append(data)

print("* done recording")

stream.stop_stream()
stream.close()
p.terminate()

wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)
wf.writeframes(b''.join(frames))
wf.close()

录音并画出每块的波形

import numpy,time

import pylab
import pyaudio
import wave

wf=wave.open("ok.wav","rb")

da=[]

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

data=wf.readframes(1000)
while data !=" ":
    stream.write(data)
    da.append(data)
    data=wf.readframes(1000)

dd=numpy.fromstring(frames,dtype=numpy.int16)
pylab.plot(dd)
pylab.savefig("kkkk.png",dpi=100)
pylab.show(block=False)
time.sleep(10)
pylab.close()

stream.stop_stream()
stream.close()
p.terminate()