python实现人工智能语音助手

一.环境搭建：

1.安装pycharm和Anaconda（安装过程几乎点下一步即可，实在怕出问题去问度娘）

2.使用Anaconda里的包模块：

 

 

 二.百度语音（STT）和图灵机器人

1.创建应用

 记住AppID、API Key、Secret Key

2.为应用获取语音识别调用次数

 

 3.创建图灵机器人

 记住apikey

三.代码复现

import speech_recognition as sr
import win32com.client
from aip import AipSpeech
import requests
import json

speaker = win32com.client.Dispatch("SAPI.SpVoice")

#使用语音识别包录制音频
def my_record(rate=16000):
    r = sr.Recognizer()
    with sr.Microphone(sample_rate=rate) as source:
        print("please say something")
        audio = r.listen(source)

    with open("recording.wav","wb") as f:
        f.write(audio.get_wav_data())
    print("录音完成")

#音频文件转文字：采用百度的语音识别python-SDK

APP_ID = 'your_ID'
API_KEY = 'your_KEY'
SECRET_KEY = 'your_SECERT_KEY'
client = AipSpeech(APP_ID,API_KEY,SECRET_KEY)
path = 'recording.wav'

#将语音转文本STT
def listen():
    #读取录音文件
    with open(path,'rb') as fp:
        voices = fp.read()
    try:
        result = client.asr(voices,'wav',16000,{'dev_pid':1537,})
        result_text = result["result"][0]
        print("you said:"+result_text)
        return result_text
    except KeyError:
        print("KeyError")
        speaker.Speak("我没有听清楚，请再说一遍...")

#调用图灵机器人
turing_api_key = "your_key"
api_url = "http://openapi.tuling123.com/openapi/api/v2"
headers = {'Content-Type':'application/json;charset=UTF-8'}

# 图灵机器人回复
def Turing(text_words=""):
    req = {
        "reqType": 0,
        "perception": {
            "inputText": {
                "text": text_words
            },

            "selfInfo": {
                "location": {
                    "city": "长沙",
                    "province": "湖南",
                    "street": "中意三路"
                }
            }
        },
        "userInfo": {
            "apiKey": turing_api_key,  # 你的图灵机器人apiKey
            "userId": "687948"  # 用户唯一标识(随便填, 非密钥)
        }
    }

    req["perception"]["inputText"]["text"] = text_words
    response = requests.request("post", api_url, json=req, headers=headers)
    response_dict = json.loads(response.text)

    result = response_dict["results"][0]["values"]["text"]
    print("AI Robot said: " + result)
    return result

# 语音合成，输出机器人的回答
while True:
    my_record()
    request = listen()
    response = Turing(request)
    speaker.Speak(response)

四.过程

收集音频——转文本——调用图灵机器人（返回文本回复）——文本转音频（调用系统自带的功能）