阿里云语音交互

import speech_recognition as sr
from gtts import gTTS
import os
import requests
import json
from aliyunsdkcore.client import AcsClient
from aliyunsdkcore.acs_exception.exceptions import ServerException, ClientException
from aliyunsdkchatbot.request.v20171011 import ChatRequest

def recognize_speech(audio_file):
    recognizer = sr.Recognizer()
    with sr.AudioFile(audio_file) as source:
        audio = recognizer.listen(source)

    try:
        print("识别中...")
        text = recognizer.recognize_google(audio, language='zh-CN')
        print("你说的是:", text)
        return text
    except sr.UnknownValueError:
        print("无法识别，请重试！")
        return ""
    except sr.RequestError as e:
        print("请求出错：", e)
        return ""

def text_to_speech(text, audio_file):
    tts = gTTS(text=text, lang='zh')
    tts.save(audio_file)
    os.system("mpg321 " + audio_file)

def chat_with_bot(text):
    access_key_id = "your_access_key_id"
    access_key_secret = "your_access_key_secret"
    endpoint = "your_chatbot_endpoint"

    client = AcsClient(access_key_id, access_key_secret, 'cn-shanghai')

    request = ChatRequest.ChatRequest()
    request.set_accept_format('json')
    request.set_BotId("your_bot_id")
    request.set_InstanceId("your_instance_id")
    request.set_Utterance(text)
    
    try:
        response = client.do_action_with_exception(request)
        response_data = json.loads(response)
        return response_data['Messages'][0]['Content']
    except ServerException as e:
        print("服务器异常：", e)
        return ""
    except ClientException as e:
        print("客户端异常：", e)
        return ""

if __name__ == "__main__":
    while True:
        input("按 Enter 键开始录音...")
        audio_file = "record.wav"
        os.system("arecord -D hw:1,0 -f cd -r 16000 -d 5 " + audio_file)
        text = recognize_speech(audio_file)
        if text:
            response_text = chat_with_bot(text)
            response_audio_file = "response_audio.wav"
            text_to_speech(response_text, response_audio_file)
            print("回复:", response_text)


#这个代码实现了一个完整的语音交互系统。
#用户按下Enter键开始录音，录音5秒后会自动停止。
#然后，系统会将录音文件转换为文本，并使用Chatbot服务获取智能回复。
#最后，系统将智能回复文本转换为语音，并播放给用户。
#请确保替换代码中的相应信息，比如阿里云的AccessKey、Chatbot的Endpoint以及录音设备的参数。