Python+pyaudio實(shí)現(xiàn)音頻控制示例詳解
更新時(shí)間：2022年07月22日 17:21:11 作者：小樹(shù)筆記
PyAudio?是語(yǔ)音處理的?Python?庫(kù)，提供了比較豐富的功能。本文將利用pyaudio控制指定設(shè)備，實(shí)現(xiàn)錄制音頻、采集音頻流、播放音頻，感興趣的可以了解一下
簡(jiǎn)介
PyAudio是一個(gè)跨平臺(tái)的音頻處理工具包，使用該工具包可以在Python程序中播放和錄制音頻，也可以產(chǎn)生wav文件等
安裝
pip install PyAudio
注意：使用該命令安裝時(shí)可能會(huì)報(bào)錯(cuò)，報(bào)錯(cuò)內(nèi)容如下：
針對(duì)該問(wèn)題，我們使用whl文件進(jìn)行安裝，首先在網(wǎng)址下面找到以下文件并下載，根據(jù)自己的python版本及計(jì)算機(jī)系統(tǒng)下載相應(yīng)文件即可。
下載完成后，切換到文件所在目錄，使用如下命令安裝即可
pip3 install PyAudio-0.2.11-cp38-cp38-win_amd64.whl
pyaudio控制指定設(shè)備，錄制音頻/采集音頻流/播放音頻
#!/usr/bin/env python3
#-*- coding:utf-8 -*-
#------------- 音頻設(shè)備操作模塊 -------------------
#
# 功能: 錄制/獲取音頻流/播放音頻
# 時(shí)間： 2021-09-13
#
#--------------------------------------------------
import sys ,pyaudio, wave
from tqdm import tqdm
class UacAudioInAndOut:
def __init__(self):
"""
功能: 錄音參數(shù)初始化
創(chuàng)建vad檢測(cè)模塊對(duì)象
參數(shù): /
返回值: /
"""
self.input_format_dict = {"S8_LE":16, "S16_LE":8, "S24_LE":4, "S32_LE":2}
self.framerate_list = [8000, 11025, 16000, 22050, 32000, 44100, 48000,
88200, 96000, 176400, 192000, 352800, 384000]
def _inforPrintf(self, infor_content):
"""
功能: 檢測(cè)操作系統(tǒng)，使用正確編碼
輸出打印信息
參數(shù): infor_content: 信息內(nèi)容
返回值: /
"""
if sys.platform != "linux" and sys.platform != "darwin":
infor_content = str(infor_content).encode("gbk","ignore").decode("gbk")
print(infor_content)
def GetAllDevInfor(self):
"""
功能: 顯示支持設(shè)備信息
參數(shù): /
返回值: /
"""
PA = pyaudio.PyAudio()
self._inforPrintf("----------------------< 本機(jī)支持設(shè)備 >------------------------------")
for dev_index in range(PA.get_device_count()):
self._inforPrintf("\n-------------------------------------------------------")
for key in PA.get_device_info_by_index(dev_index):
self._inforPrintf("%s:%s"%(key, str(PA.get_device_info_by_index(dev_index)[key])))
self._inforPrintf("========================================================")
def GetUacDevInfor(self, devKeywordOrIndex=None):
"""
功能: 獲取UAC設(shè)備信息
參數(shù): devKeywordOrIndex: 設(shè)備名稱關(guān)鍵字或索引
返回值: dic 設(shè)備信息字典
False 設(shè)備信息獲取失敗
"""
PA = pyaudio.PyAudio()
if devKeywordOrIndex == None:
self._inforPrintf("\033[0;36;31m[UacAudioInAndOut] 未設(shè)設(shè)備, 當(dāng)前使用默認(rèn)設(shè)備\033[0m")
return PA.get_default_input_device_info()
if str(devKeywordOrIndex).isdigit():
devKeywordOrIndex = int(devKeywordOrIndex)
return PA.get_device_info_by_index(devKeywordOrIndex)
uac_infor_list = []
for uac_index in range(PA.get_device_count()):
if PA.get_device_info_by_index(uac_index).get("name").find(str(devKeywordOrIndex)) >= 0:
uac_infor_list.append(PA.get_device_info_by_index(uac_index))
if len(uac_infor_list) > 1:
self._inforPrintf("\033[0;36;33m[UacAudioInAndOut] UAC 設(shè)備有多個(gè)，\
請(qǐng)修正關(guān)鍵字, 當(dāng)前設(shè)備如下: %s\033[0m"%str(uac_infor_list))
return False
else:
return uac_infor_list.pop()
def is_framerate_supported(self, setFramerate, UacAudioInHandle,
load_parame_dict, input_or_output="input"):
"""
功能: 判斷當(dāng)配置在指定設(shè)備中是否支持
參數(shù): setFramerate: 設(shè)置采樣率
UacAudioInHandle: 設(shè)備句柄
load_parame_dict: 加載字典
input_or_output: 輸入/輸出功能
返回值: bool True/False
"""
try:
if input_or_output == "input":
UacAudioInHandle.is_format_supported(rate=float(setFramerate),
input_device=load_parame_dict['index'],
input_channels=load_parame_dict['setInputChannels'],
input_format=load_parame_dict['_setInputFormat'])
else:
UacAudioInHandle.is_format_supported(rate=float(setFramerate),
output_device=load_parame_dict['index'],
output_channels=load_parame_dict['maxOutputChannels'],
output_format=UacAudioInHandle.get_format_from_width(load_parame_dict['setOutputFormat']))
return True
except:
return False
def LoadUacAudioInDevice(self, maxStreamDuration=1000, setInputChannels=None,
setInputFormat=None, devKeywordOrIndex=None):
"""
功能: 加載音頻獲取設(shè)備
參數(shù): maxStreamDuration=1000 默認(rèn)一段流時(shí)長(zhǎng)
setInputChannels: 通道數(shù)
setInputFormat: 位寬
devKeywordOrIndex: 錄音設(shè)備關(guān)鍵字/索引
返回值:
成功: UacAudioInHandle, StreamHandle, load_parame_dict
失敗: False
"""
try:
load_parame_dict = {}
uac_infor_dict = self.GetUacDevInfor(devKeywordOrIndex)
if not setInputFormat:
_Format = "S16_LE"
self._inforPrintf("\033[0;36;33m[UacAudioInAndOut] 未設(shè)置位寬，使用默認(rèn) S16_LE \033[0m")
else:
_Format = setInputFormat
setInputFormat = self.input_format_dict[_Format]
if not setInputChannels or int(setInputChannels) > uac_infor_dict["maxInputChannels"]:
setInputChannels = uac_infor_dict["maxInputChannels"]
self._inforPrintf("\033[0;36;33m[UacAudioInAndOut] 輸入通道未設(shè)置/超出當(dāng)前設(shè)備最大值,使用默認(rèn)最大通道 %s\
\033[0m"%setInputChannels)
else:
setInputChannels = int(setInputChannels)
dev_index = uac_infor_dict["index"]
load_parame_dict["index"]=dev_index
load_parame_dict["setInputFormat"] = _Format
load_parame_dict["_setInputFormat"] = setInputFormat
load_parame_dict["setInputChannels"] = setInputChannels
UacAudioInHandle = pyaudio.PyAudio()
for setInputFramerate in self.framerate_list:
if self.is_framerate_supported(setInputFramerate, UacAudioInHandle, load_parame_dict):
load_parame_dict["setInputFramerate"] = setInputFramerate
break
#計(jì)算數(shù)據(jù)大小一段
CHUNK_SIZE = int(setInputFramerate * maxStreamDuration / 1000)
load_parame_dict["CHUNK_SIZE"] = CHUNK_SIZE
self._inforPrintf("\033[0;36;38m[UacAudioInAndOut] 加載參數(shù): %s\033[0m"%str(load_parame_dict))
#加載設(shè)備
StreamHandle = UacAudioInHandle.open(
format=load_parame_dict['_setInputFormat'],
channels=load_parame_dict['setInputChannels'],
rate=load_parame_dict['setInputFramerate'],
input=True,
input_device_index=load_parame_dict['index'],
start=False,
frames_per_buffer=int(CHUNK_SIZE))
#開(kāi)始流獲取
StreamHandle.start_stream()
return UacAudioInHandle, StreamHandle, load_parame_dict
except:
self._inforPrintf("\033[0;36;31m[UacAudioInAndOut] Uac AudioIn 加載失敗\033[0m")
return False, False, False
def LoadUacAudioOutDevice(self, devKeywordOrIndex):
"""
功能: 加載音頻輸出設(shè)備
參數(shù): /
返回值: UacAudioInHandle 或 False
"""
try:
uac_infor_dict = self.GetUacDevInfor(devKeywordOrIndex)
UacAudioInHandle = pyaudio.PyAudio()
return UacAudioInHandle, uac_infor_dict
except:
return False
def GetUacAudioInStream(self, StreamHandle, CHUNK_SIZE):
"""
功能: 開(kāi)始采集聲卡音頻
生成音頻流
參數(shù): UacAudioInHandle: 設(shè)備句柄
StreamHandle: 流句柄
返回值 chunk_data 流數(shù)據(jù)
"""
return StreamHandle.read(CHUNK_SIZE, exception_on_overflow=False) #防止溢出
def UacAudioOutPlay(self, playWavFile, Repeat=None, Pdict=None, devKeywordOrIndex=None,):
"""
功能: 可以循環(huán)播放指定文件
參數(shù): playWavFile: 播放文件路徑
Repeat: 循環(huán)播放次數(shù)
CustomizeAudioParam: 自定義播放參數(shù)
返回值: /
"""
UacAudioInHandle, uac_infor_dict = self.LoadUacAudioOutDevice(devKeywordOrIndex)
self._inforPrintf(str(uac_infor_dict).encode("gbk","ignore").decode("gbk"))
self._inforPrintf("\033[1;36;34m[UacAudioInAndOut] 指定設(shè)備: %s\t播放文件: %s\t循環(huán)總數(shù): %s\
\033[0m"%(devKeywordOrIndex, playWavFile,Repeat))
try:
chunk=1024
pfb = wave.open(playWavFile, 'rb')
setOutputFormat = pfb.getsampwidth()
setOutputChannels = pfb.getnchannels()
setOutputFramerate = pfb.getframerate()
uac_infor_dict['setOutputFormat'] = setOutputFormat
if setOutputChannels > uac_infor_dict["maxOutputChannels"]:
self._inforPrintf("\033[0;36;31m[UacAudioInAndOut] 當(dāng)前通道數(shù)，在該設(shè)備上不支持, \
設(shè)備最大通道數(shù): %s\033[0m"%uac_infor_dict["maxOutputChannels"])
return False
if not self.is_framerate_supported(setOutputFramerate, UacAudioInHandle, uac_infor_dict, "output"):
self._inforPrintf("\033[0;36;31m[UacAudioInAndOut] 當(dāng)前文件采樣率，在該設(shè)備上不支持,\
設(shè)備默認(rèn)采樣率: %s\033[0m"%uac_infor_dict["defaultSampleRate"])
return False
else:
uac_infor_dict["defaultSampleRate"] = setOutputFramerate
stream = UacAudioInHandle.open(
output_device_index=uac_infor_dict['index'],
format=UacAudioInHandle.get_format_from_width(setOutputFormat),
channels=setOutputChannels,
rate=setOutputFramerate,
output=True)
if Repeat == "Dead_cycle":
self._inforPrintf("\033[1;36;33m[UacAudioInAndOut] Dead cycle play !!! \033[0m")
while True:
if type(Pdict) == dict and Pdict["play status"] == "stop":
break
pfb = wave.open(playWavFile, 'rb')
while True:
data = pfb.readframes(chunk)
if not data:
break
stream.write(data)
else:
for index in tqdm(range(int(Repeat))):
if type(Pdict) == dict and Pdict["play status"] == "stop":
break
pfb = wave.open(playWavFile, 'rb')
while True:
data = pfb.readframes(chunk)
if not data:
break
stream.write(data)
stream.stop_stream()
stream.close()
self.CloseAudioDevice(UacAudioInHandle)
return True
except:
stream.stop_stream()
stream.close()
return False
def UacAudioInRecord(self, saveWavFile, recordTime, #單位秒
setInputChannels=None,
setInputFormat=None,
devKeywordOrIndex=None):
"""
功能: 錄制音頻文件
參數(shù): recordTime: 錄音時(shí)長(zhǎng), 單位(s)
setInputFramerate: 采樣率
setInputChannels: 通道數(shù)
setInputFormat: 位寬
devKeywordOrIndex: 錄音設(shè)備索引
返回值: /
"""
maxStreamDuration=1000
load_parame_dict = {}
UacAudioInHandle, StreamHandle, load_parame_dict = self.LoadUacAudioInDevice(
maxStreamDuration,
setInputChannels,
setInputFormat,
devKeywordOrIndex)
if not UacAudioInHandle or not StreamHandle:
self._inforPrintf("\033[0;36;31m[UacAudioInAndOut] 錄音失敗\033[0m")
return False
self._inforPrintf("\033[1;36;34m[UacAudioInAndOut] 錄音 -> 文件名: %s 時(shí)長(zhǎng): %s\
\033[0m"%(saveWavFile,recordTime))
self._inforPrintf(load_parame_dict["CHUNK_SIZE"])
data_list = []
for recordTime_index in range(int(recordTime)):
data = None
data = StreamHandle.read(load_parame_dict["CHUNK_SIZE"], exception_on_overflow=False)
data_list.append(data)
StreamHandle.stop_stream()
StreamHandle.close()
self.CloseAudioDevice(UacAudioInHandle)
with wave.open(saveWavFile, "wb") as wavfb:
wavfb.setnchannels(load_parame_dict["setInputChannels"])
wavfb.setsampwidth(UacAudioInHandle.get_sample_size(load_parame_dict["_setInputFormat"]))
wavfb.setframerate(load_parame_dict["setInputFramerate"])
wavfb.writeframes(b''.join(data_list))
"""
功能: 關(guān)閉音頻流設(shè)備
參數(shù): UacAudioInHandle
返回值: bool True/False
"""
try:
StreamHandle.stop_stream()
StreamHandle.close()
self.CloseAudioDevice()
return True
except:
return False
def CloseAudioDevice(self, UacAudioDeviceHandle):
"""
功能: 釋放 Audio 設(shè)備
參數(shù): UacAudioDeviceHandle
返回值: bool True/False
"""
try:
UacAudioDeviceHandle.terminate()
return True
except:
return False
if __name__=="__main__":
asv = UacAudioInAndOut()
asv.GetAllDevInfor()
#asv.UacAudioOutPlay(sys.argv[1], int(sys.argv[2]), None, sys.argv[3])
asv.UacAudioInRecord(sys.argv[1], sys.argv[2])以上就是Python+pyaudio實(shí)現(xiàn)音頻控制示例詳解的詳細(xì)內(nèi)容，更多關(guān)于Python pyaudio音頻控制的資料請(qǐng)關(guān)注腳本之家其它相關(guān)文章！
相關(guān)文章
Python?工程師在日常的工作中，經(jīng)常會(huì)碰到解析和處理PDF文件的情況。本文將pdfplumber進(jìn)行PDF文件的讀取操作，感興趣的可以了解一下2022-08-08
在 Django 的開(kāi)發(fā)過(guò)程中,查詢集（QuerySet）是我們與數(shù)據(jù)庫(kù)進(jìn)行交互的重要工具,本文將深入探討 Django 查詢集的延遲加載特性,幫助新手理解其工作原理及優(yōu)缺點(diǎn),提供一些實(shí)用的代碼示例來(lái)展示延遲加載如何在實(shí)際項(xiàng)目中使用,需要的朋友可以參考下2024-10-10
Python 爬蟲之Beautiful Soup模塊使用指南
這篇文章主要介紹了Python 爬蟲之Beautiful Soup模塊使用指南，小編覺(jué)得挺不錯(cuò)的，現(xiàn)在分享給大家，也給大家做個(gè)參考。一起跟隨小編過(guò)來(lái)看看吧2018-07-07
Python如何基于rsa模塊實(shí)現(xiàn)非對(duì)稱加密與解密
這篇文章主要介紹了Python如何基于rsa模塊實(shí)現(xiàn)非對(duì)稱加密與解密,文中通過(guò)示例代碼介紹的非常詳細(xì)，對(duì)大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價(jià)值,需要的朋友可以參考下2020-01-01
Python 經(jīng)典貪心算法之Prim算法案例詳解
這篇文章主要介紹了Python 經(jīng)典貪心算法之Prim算法案例詳解,本篇文章通過(guò)簡(jiǎn)要的案例,講解了該項(xiàng)技術(shù)的了解與使用,以下就是詳細(xì)內(nèi)容,需要的朋友可以參考下2021-09-09
tensorflow 實(shí)現(xiàn)自定義梯度反向傳播代碼
今天小編就為大家分享一篇tensorflow 實(shí)現(xiàn)自定義梯度反向傳播代碼，具有很好的參考價(jià)值，希望對(duì)大家有所幫助。一起跟隨小編過(guò)來(lái)看看吧2020-02-02
這篇文章主要介紹了Python docx庫(kù)用法,結(jié)合實(shí)例形式分析了docx庫(kù)相關(guān)的docx文件讀取、文本添加、格式操作,需要的朋友可以參考下2021-10-10
利用python實(shí)現(xiàn)簡(jiǎn)單的郵件發(fā)送客戶端示例
下面小編就為大家分享一篇利用python實(shí)現(xiàn)簡(jiǎn)單的郵件發(fā)送客戶端示例，具有很好的參考價(jià)值，希望對(duì)大家有所幫助。一起跟隨小編過(guò)來(lái)看看吧2017-12-12
在本篇文章里小編給大家整理了關(guān)于python中數(shù)字是否為可變類型的相關(guān)文章內(nèi)容，需要的朋友們可以學(xué)習(xí)下。2020-07-07
關(guān)于keras中卷積層Conv2D的學(xué)習(xí)記錄
這篇文章主要介紹了關(guān)于keras中卷積層Conv2D的學(xué)習(xí)記錄，具有很好的參考價(jià)值，希望對(duì)大家有所幫助。如有錯(cuò)誤或未考慮完全的地方，望不吝賜教2023-02-02