人工智能---语音合成识别图灵机械人语音交互

""" 你的 APPID AK SK """
import os
from aip import AipSpeech, AipNlp
from ss import tuling
from ss.录音 import rec

APP_ID = '16027699'
API_KEY = 'rZrseMjmXXHadrp0fbUAyb6Z'
SECRET_KEY = '0tFVGEW09PpPCMxXBqVrda59fQf3wY3c'

client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)
client_NLp = AipNlp(APP_ID, API_KEY, SECRET_KEY)


#文字合成语音
def text_audio(text):
    result = client.synthesis(text, 'zh', 1, {
        'vol': 5,
        'per': 4,
        'pit': 8,
        'spd': 5,
    })

    # 识别正确返回语音二进制 错误则返回dict 参照下面错误码
    if not isinstance(result, dict):
        with open('audios1.mp3', 'wb') as f:
            f.write(result)
    return 'audios1.mp3'

#语音识别--文字
def audio_text(filename):
    # 识别本地文件
    res = client.asr(get_file_content(filename), 'pcm', 16000, {
        'dev_pid': 1536,
    })
    return res.get('result')[0]


# -转换格式--读取文件
def get_file_content(filePath):
    os.system(f"ffmpeg -y  -i {filePath}.wav  -acodec pcm_s16le -f s16le -ac 1 -ar 16000 {filePath}.pcm ")
    with open(f'{filePath}.pcm', 'rb') as fp:
        return fp.read()


if __name__ == '__main__':

    re=rec('file_name.wav')  #录音,形成录音文件
    text=audio_text('file_name')  #录音转为文字
    # print(text)
    # score =client_NLp.simnet(text,'今天天气').get('score')
    # print(score)
    # if score>0.58:
    #     print('1111')
    #     filename=text_audio('是呀,撩起呀!')
    #     print(filename)
    #     # os.system(f"ffplay {filename}")
    #     os.system(filename)

    answer=tuling.get_help_from_tuling(text,'mabing') #文字信息传递给tuling得到答复信息
    filename = text_audio(answer)  #答复信息再转为语音
    os.system(filename)            #播放

另外还有几个.py文件

tuling.py  #与图灵机器人连接

import requests

def get_help_from_tuling(text,uid):
    URL = 'http://openapi.tuling123.com/openapi/api/v2'

    data = {
        "perception": {
            "inputText": {
                "text": ''
            }
        },
        "userInfo": {
            "apiKey": "86fd93bd29e941eebe314766616a3f15",
            "userId": "123456"
        }
    }
    data["perception"]["inputText"]["text"] = text
    data["userInfo"]["userId"] = uid
    res = requests.post(URL, json=data)
    print(res.json())
    return res.json().get('results')[0].get('values').get('text')

录音文件,通过执行函数,就会形成语音文件

import pyaudio
import wave

CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 2
RATE = 16000
RECORD_SECONDS = 6
# WAVE_OUTPUT_FILENAME = "Oldboy.wav"
def rec(file_name):
    p = pyaudio.PyAudio()

    stream = p.open(format=FORMAT,
                    channels=CHANNELS,
                    rate=RATE,
                    input=True,
                    frames_per_buffer=CHUNK)

    print("开始录音,请说话......")

    frames = []

    for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
        data = stream.read(CHUNK)
        frames.append(data)

    print("录音结束,请闭嘴!")

    stream.stop_stream()
    stream.close()
    p.terminate()

    wf = wave.open(file_name, 'wb')
    wf.setnchannels(CHANNELS)
    wf.setsampwidth(p.get_sample_size(FORMAT))
    wf.setframerate(RATE)
    wf.writeframes(b''.join(frames))
    wf.close()