基于百度API和图灵机器人的智能语音聊天机器人

简单的流程就是语音交给百度API转换成文字，

文字提交给图灵机器人返回文字回答，

将返回的文字交给百度再转换成语音输出。

sox这个不太好装，可以参考 http://www.plane.run/306.py

其他的库直接pip3 install 都可以正常装上。

import os
import time
import wave
import json
import pyaudio
import requests
import speech_recognition as sr
from aip import AipSpeech

# 百度
APP_ID = ' '
API_KEY = ' '
SECRET_KEY = ' '

client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)



# 图灵机器人
TURING_KEY = " "
URL = "http://openapi.turingapi.com/openapi/api/v2"
HEADERS = {'Content-Type': 'application/json;charset=UTF-8'}

# 用 SpeechRecognition 录音
def rec(rate=16000):
    r = sr.Recognizer()
    with sr.Microphone(sample_rate=rate) as source:
        print("[话痨版小飞] 正在等你说话...")
        audio = r.listen(source)

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


#  百度语音AI 语音转文字
def listen():
    with open('recording.wav', 'rb') as f:
        audio_data = f.read()

    result = client.asr(audio_data, 'wav', 16000, {
        'dev_pid': 1536,
    })
#    print(result)
    if  "result" in result.keys():
        result_text = result["result"][0]
    else:
        result_text = "我沉默了"

    print("你说: " + result_text)

    return result_text


  图灵机器人
def robot(text=""):
    data = {
        "reqType": 0,
        "perception": {
            "inputText": {
                "text": ""
            },
            "selfInfo": {
                "location": {
                    "city": "威海",
                    "street": "古寨东路"
                }
            }
        },
        "userInfo": {
            "apiKey": TURING_KEY,
            "userId": "starky"
        }
    }

    data["perception"]["inputText"]["text"] = text
    response = requests.request("post", URL, json=data, headers=HEADERS)
    response_dict = json.loads(response.text)

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

#  百度语音AI 文字转语音
def speak(text=""):
    result = client.synthesis(text, 'zh', 1, {
        'spd': 5,
        'vol': 5,
        'per': 4,
    })

    if not isinstance(result, dict):
        with open('audio.mp3', 'wb') as f:
            f.write(result)


# 转换MP3 到wav播放  因为百度返回的只能是mp3格式 多了一步转换
def play():
    os.system('sox audio.mp3 audio.wav')
    wf = wave.open('audio.wav', 'rb')
    p = pyaudio.PyAudio()

    def callback(in_data, frame_count, time_info, status):
        data = wf.readframes(frame_count)
        return (data, pyaudio.paContinue)

    stream = p.open(format=p.get_format_from_width(wf.getsampwidth()),
                    channels=wf.getnchannels(),
                    rate=wf.getframerate(),
                    output=True,
                    stream_callback=callback)

    stream.start_stream()

    while stream.is_active():
        time.sleep(0.1)

    stream.stop_stream()
    stream.close()
    wf.close()

    p.terminate()


while True:
    rec()
    request = listen()
    response = robot(request)
    speak(response)
    play()