使用pyaudio录音

Question

我正在尝试使用 python 录制语音。我尝试使用 pyaudio 模块，它在我的电脑上保存了一个 wav 文件，但录制了一个静态声音。有什么建议？

import pyaudio
import wave

CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 2
RATE = 44100
RECORD_SECONDS = 5
WAVE_OUTPUT_FILENAME = "voice.wav"

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()

Answer 1

首先，确保您的麦克风已实际连接、打开且未静音。

打开流时您没有提供设备索引。这意味着您将获得 PyAudio 认为默认的设备。这可能不是您的麦克风。

在交互式 Python 会话中使用对象的get_device_count和get_device_info_by_index方法PyAudio。打印get_device_info_by_index返回的字典以确定哪个设备索引代表您的麦克风，并input_device_index在打开流时提供该索引号作为参数。

Answer 2

下面的代码将列出可用录音设备的索引，然后用户可以给出特定的索引作为输入，代码将通过给定的录音设备索引开始录音。

import pyaudio
import wave
 
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 44100
CHUNK = 512
RECORD_SECONDS = 5
WAVE_OUTPUT_FILENAME = "recordedFile.wav"
device_index = 2
audio = pyaudio.PyAudio()

print("----------------------record device list---------------------")
info = audio.get_host_api_info_by_index(0)
numdevices = info.get('deviceCount')
for i in range(0, numdevices):
        if (audio.get_device_info_by_host_api_device_index(0, i).get('maxInputChannels')) > 0:
            print("Input Device id ", i, " - ", audio.get_device_info_by_host_api_device_index(0, i).get('name'))

print("-------------------------------------------------------------")

index = int(input())
print("recording via index "+str(index))

stream = audio.open(format=FORMAT, channels=CHANNELS,
                rate=RATE, input=True,input_device_index = index,
                frames_per_buffer=CHUNK)
print ("recording started")
Recordframes = []
 
for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
    data = stream.read(CHUNK)
    Recordframes.append(data)
print ("recording stopped")
 
stream.stop_stream()
stream.close()
audio.terminate()
 
waveFile = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
waveFile.setnchannels(CHANNELS)
waveFile.setsampwidth(audio.get_sample_size(FORMAT))
waveFile.setframerate(RATE)
waveFile.writeframes(b''.join(Recordframes))
waveFile.close()