Python只需要三十行代码，打造一款简单的人工语音对话_could not request results from google speech recog

gtts
gtts是将文字转化为语音，但是需要在VPN下使用。这个因为要接谷歌服务器。

具体gtts的官方文档：

下面，让我们看一段简单的的代码

from gtts import gTTS

def speak(audioString):
    print(audioString)
    tts = gTTS(text=audioString, lang='en')
    tts.save("audio.mp3")
    os.system("audio.mp3")
    
speak("Hi Runsen, what can I do for you?")

1
2
3
4
5
6
7
8
9
10

执行上面的代码，就可以生成一个mp3文件，播放就可以听到了Hi Runsen, what can I do for you?。这个MP3会自动弹出来的。

speech_recognition
speech_recognition用于执行语音识别的库，支持在线和离线的多个引擎和API。

speech_recognition具体官方文档

安装speech_recognition可以会出现错误，对此解决的方法是通过该网址安装对应的whl包

在官方文档中提供了具体的识别来自麦克风的语音输入的代码

下面就是 speech_recognition 用麦克风记录下你的话，这里我使用的是
recognize_google，speech_recognition 提供了很多的类似的接口。

import time
import speech_recognition as sr

# 录下来你讲的话
def recordAudio():
    # 用麦克风记录下你的话
    print("开始麦克风记录下你的话")
    r = sr.Recognizer()
    with sr.Microphone() as source:
        audio = r.listen(source)
    data = ""
    try:
        data = r.recognize_google(audio)
        print("You said: " + data)
    except sr.UnknownValueError:
        print("Google Speech Recognition could not understand audio")
    except sr.RequestError as e:
        print("Could not request results from Google Speech Recognition service; {0}".format(e))
    return data

if __name__ == '__main__':
    time.sleep(2)
    while True:
        data = recordAudio()
        print(data)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26

下面是我乱说的英语

对话
上面，我们实现了用麦克风记录下你的话，并且得到了对应的文本，那么下一步就是字符串的文本操作了，比如说how are you，那回答"I am fine”，然后将"I am fine”通过gtts是将文字转化为语音

# @Author：Runsen
# -*- coding: UTF-8 -*-
import speech_recognition as sr
from time import ctime
import time
import os
from gtts import gTTS


# 讲出来AI的话
def speak(audioString):
    print(audioString)
    tts = gTTS(text=audioString, lang='en')
    tts.save("audio.mp3")
    os.system("audio.mp3")


# 录下来你讲的话
def recordAudio():
    # 用麦克风记录下你的话
    r = sr.Recognizer()
    with sr.Microphone() as source:
        audio = r.listen(source)

    data = ""
    try:
        data = r.recognize_google(audio)
        print("You said: " + data)
    except sr.UnknownValueError:
        print("Google Speech Recognition could not understand audio")
    except sr.RequestError as e:
        print("Could not request results from Google Speech Recognition service; {0}".format(e))

    return data


# 自带的对话技能（逻辑代码：rules）
def jarvis():
    while True:
        data = recordAudio()
        print(data)
        if "how are you" in data:
            speak("I am fine")
        if "time" in data:
            speak(ctime())
        if "where is" in data:
            data = data.split(" ")
            location = data[2]
            speak("Hold on Runsen, I will show you where " + location + " is.")
            # 打开谷歌地址
            os.system("open -a Safari https://www.google.com/maps/place/" + location + "/&")

        if "bye" in data:
            speak("bye bye")
            break


if __name__ == '__main__':
    # 初始化
    time.sleep(2)
    speak("Hi Runsen, what can I do for you?")

    # 跑起
    jarvis()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65

当我说how are you？会弹出I am fine的mp3

当我说where is Chiana？会弹出Hold on Runsen, I will show you where China is.的MP3