---

前言

现在语音助手已经成为我们生活中ai的代表，下面让我们看一下语音助手的语音输入功能

---

准备

1. 让我们搜索一下百度的开放平台

2. 进入百度开放平台后选择短语音识别
   

3. 然后去领取免费的资源
   

4. 创建应用
   

5. 记住相关的key
   

下载库

本次用到的库（以及引入方法）：

import speech_recognition as sr
from aip import AipSpeech
import pyttsx3

代码实现以及

编写我的key

APP_ID = '27468776'
API_KEY = 'ygQgtR4DIh14lDi8gwSMCm7o'
SECRET_KEY = '7flGlZba42ZYxHudy3dSQ8YW4n89W5hc'
client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)

语音的录入：

try:
    def rec(rate=16000):
        r = sr.Recognizer()
        with sr.Microphone(sample_rate=rate) as source:
            print("请说话")
            audio = r.listen(source)

        with open("recording.wav", "wb") as f:
            f.write(audio.get_wav_data())
except:
    print("语音录入发生错误")

使用百度语音作为STT引擎并通过pyttsx3函数将返回的内容读出来形成简单的对话

    with open('recording.wav', 'rb') as f:
        audio_data = f.read()

        result = client.asr(audio_data, 'wav', 16000, {
        'dev_pid': 1536,
    })
        try:
            result_text = result["result"][0]
            print("你说: " + result_text)


            if result_text =="于金龙":
                engine = pyttsx3.init()
                engine.say('真帅')
                engine.runAndWait()
            elif result_text=="张新凯":
                engine = pyttsx3.init()
                engine.say('真难看')
                engine.runAndWait()
        except:
            print("没有识别到语音")

完整代码

import pyttsx3

import speech_recognition as sr
from aip import AipSpeech

# Baidu Speech API, replace with your personal key
APP_ID = '27468776'
API_KEY = 'ygQgtR4DIh14lDi8gwSMCm7o'
SECRET_KEY = '7flGlZba42ZYxHudy3dSQ8YW4n89W5hc'

client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)

# Use SpeechRecognition to record
try:
    def rec(rate=16000):
        r = sr.Recognizer()
        with sr.Microphone(sample_rate=rate) as source:
            print("请说话")
            audio = r.listen(source)

        with open("recording.wav", "wb") as f:
            f.write(audio.get_wav_data())
except:
    print("语音录入发生错误")


# 使用百度语音作为STT引擎
def listen():
    with open('recording.wav', 'rb') as f:
        audio_data = f.read()

        result = client.asr(audio_data, 'wav', 16000, {
        'dev_pid': 1536,
    })
        try:
            result_text = result["result"][0]
            print("你说: " + result_text)


            if result_text =="阿龙":
                engine = pyttsx3.init()
                engine.say('真帅')
                engine.runAndWait()
            elif result_text=="其他人":
                engine = pyttsx3.init()
                engine.say('真难看')
                engine.runAndWait()
        except:
            print("没有识别到语音")


while True:
    rec()
    request = listen()

运行结果