Python3从零搭建语音对话机器人：百度AI与图灵机器人实战

import speech_recognition as sr
 
# Use SpeechRecognition to record 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("voices/myvoices.wav", "wb") as f:
    f.write(audio.get_wav_data())
  print("录音完成！")
 
my_record()

import wave
from pyaudio import PyAudio, paInt16
 
framerate = 16000 # 采样率
num_samples = 2000 # 采样点
channels = 1 # 声道
sampwidth = 2 # 采样宽度2bytes
FILEPATH = 'voices/myvoices.wav'
 
 
def save_wave_file(filepath, data):
  wf = wave.open(filepath, 'wb')
  wf.setnchannels(channels)
  wf.setsampwidth(sampwidth)
  wf.setframerate(framerate)
  wf.writeframes(b''.join(data))
  wf.close()
 
 
#录音
def my_record():
  pa = PyAudio()
  #打开一个新的音频stream
  stream = pa.open(format=paInt16, channels=channels,
           rate=framerate, input=True, frames_per_buffer=num_samples)
  my_buf = [] #存放录音数据
 
  t = time.time()
  print('正在录音...')
 
  while time.time() < t + 10: # 设置录音时间（秒）
  	#循环read，每次read 2000frames
    string_audio_data = stream.read(num_samples)
    my_buf.append(string_audio_data)
  print('录音结束.')
  save_wave_file(FILEPATH, my_buf)
  stream.close()

# 音频文件转文字：采用百度的语音识别python-SDK
# 百度语音识别API配置参数
from aip import AipSpeech
 
APP_ID = 'your app_id'
API_KEY = 'your api_key'
SECRET_KEY = 'your secret_key'
client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)
path = 'voices/myvoices.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:
    # 参数dev_pid：1536普通话(支持简单的英文识别)、1537普通话(纯中文识别)、1737英语、1637粤语、1837四川话、1936普通话远场
    result = client.asr(voices, 'wav', 16000, {'dev_pid': 1537, })
    # result = CLIENT.asr(get_file_content(path), 'wav', 16000, {'lan': 'zh', })
    # print(result)
    # print(result['result'][0])
    # print(result)
    result_text = result["result"][0]
    print("you said: " + result_text)
    return result_text
  except KeyError:
    print("KeyError")

# 与机器人对话：调用的是图灵机器人
import requests
import json
 
# 图灵机器人的API_KEY、API_URL
turing_api_key = "your turing_api_key"
api_url = "http://openapi.tuling123.com/openapi/api/v2" # 图灵机器人api网址
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": "北京",
          "province": "北京",
          "street": "车公庄西大街"
        }
      }
    },
    "userInfo": {
      "apiKey": turing_api_key, # 你的图灵机器人apiKey
      "userId": "Nieson" # 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

import pyttsx3
 
# 初始化语音
engine = pyttsx3.init() # 初始化语音库
# 设置语速
rate = engine.getProperty('rate')
engine.setProperty('rate', rate-50)
# 输出语音
engine.say("你好，很高兴认识你！") # 合成语音
engine.runAndWait()

import win32com.client
 
speaker = win32com.client.Dispatch("SAPI.SpVoice")
speaker.Speak("我是语音助手，小灵！")

# -*- coding: utf-8 -*-#
# -------------------------------
# Name:SpeechRobot
# Author:Nieson
# Date:2019/7/19 16:31
# 用python3实现自己的语音对话机器人
# -------------------------------
 
from aip import AipSpeech
import requests
import json
import speech_recognition as sr
import win32com.client
 
# 初始化语音
speaker = win32com.client.Dispatch("SAPI.SpVoice")
 
 
# 1、语音生成音频文件,录音并以当前时间戳保存到voices文件中
# Use SpeechRecognition to record 使用语音识别录制
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("voices/myvoices.wav", "wb") as f:
    f.write(audio.get_wav_data())
 
 
# 2、音频文件转文字：采用百度的语音识别python-SDK
# 导入我们需要的模块名，然后将音频文件发送给出去，返回文字。
# 百度语音识别API配置参数
APP_ID = 'your app_id'
API_KEY = 'your api_key'
SECRET_KEY = 'your secret_key'
client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)
path = 'voices/myvoices.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:
    # 参数dev_pid：1536普通话(支持简单的英文识别)、1537普通话(纯中文识别)、1737英语、1637粤语、1837四川话、1936普通话远场
    result = client.asr(voices, 'wav', 16000, {'dev_pid': 1537, })
    # result = CLIENT.asr(get_file_content(path), 'wav', 16000, {'lan': 'zh', })
    # print(result)
    # print(result['result'][0])
    # print(result)
    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...")
 
 
# 3、与机器人对话：调用的是图灵机器人
# 图灵机器人的API_KEY、API_URL
turing_api_key = "your turing_api_key"
api_url = "http://openapi.tuling123.com/openapi/api/v2" # 图灵机器人api网址
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": "北京",
          "province": "北京",
          "street": "车公庄"
        }
      }
    },
    "userInfo": {
      "apiKey": turing_api_key, # 你的图灵机器人apiKey
      "userId": "Nieson" # 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)