Python:在语音识别中获取系统音频，而不是麦克风

import pyaudio
import wave
import numpy as np

# 获取系统音频设备列表
def get_audio_devices():
    p = pyaudio.PyAudio()
    device_list = []
    for i in range(p.get_device_count()):
        device_info = p.get_device_info_by_index(i)
        device_list.append(device_info)
    return device_list

# 获取系统音频
def get_system_audio(device_index, duration, output_file):
    CHUNK = 1024
    FORMAT = pyaudio.paInt16
    CHANNELS = 1
    RATE = 44100

    p = pyaudio.PyAudio()

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

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

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

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

# 示例用法
device_list = get_audio_devices()
for device in device_list:
    print(device['index'], device['name'])

device_index = 0  # 设置所需的系统音频设备索引
duration = 5  # 设置录制音频的时长（秒）
output_file = 'system_audio.wav'  # 设置输出音频文件名

get_system_audio(device_index, duration, output_file)