语音助手贾维斯1.0 简单

# -*- coding: utf-8 -*-
import pyaudio
import wave

CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
RECORD_SECONDS = 5

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,謝謝！")
    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()

# -*- coding: utf-8 -*-
import os

def wav_to_pcm(wav_file):
    pcm_file = "%s.pcm" %(wav_file.split(".")[0])
    os.system("ffmpeg -y  -i %s  -acodec pcm_s16le -f s16le -ac 1 -ar 16000 %s"%(wav_file,pcm_file))
    return pcm_file

# -*- coding: utf-8 -*-
import pyrec
import wav2pcm
from aip import AipSpeech
from pydub import AudioSegment #pip install pydub
from pydub.playback import play#pip install pydub
import RPi.GPIO as GPIO
pyrec.rec("rec.wav")
pcm_file=wav2pcm.wav_to_pcm("rec.wav")

#百度AI語音識別 申请地址 https://ai.baidu.com/
APP_ID = '此处替换成自己的'
API_KEY = '此处替换成自己的'
SECRET_KEY = '此处替换成自己的'
client = AipSpeech(APP_ID, API_KEY, SECRET_KEY)
def get_file_content(filePath):
    with open(filePath, 'rb') as fp:
        return fp.read()
# 识别本地文件
res=client.asr(get_file_content('rec.pcm'), 'pcm', 16000, {
    'dev_pid': 1537,
})

#反饋語音識別結果
print(res)
text = res['result'][0]
print(text)

#按照語音指令進行相關操作
if text=='贾维斯，贾维斯。':
    result = client.synthesis('緩衝 嗨～主人您今天真帥啊，', 'zh', 1, {
        'vol': 6, 'per': 4, 'spd': 5
    })
    with open('auido.mp3', 'wb') as f:
        f.write(result)
    sound = AudioSegment.from_mp3('auido.mp3')
    play(sound)
elif text=='开灯。':
    result = client.synthesis(' 緩衝 主人，燈已經打開！', 'zh', 1, {
        'vol': 6, 'per': 4, 'spd': 5
    })
    with open('auido.mp3', 'wb') as f:
        f.write(result)
    sound = AudioSegment.from_mp3('auido.mp3')
    play(sound)
    GPIO.setmode(GPIO.BCM)
    GPIO.setup(17, GPIO.OUT)
    GPIO.output(17, GPIO.HIGH)
elif text=='关灯。':
    result = client.synthesis(' 緩衝主人，燈已經關閉！', 'zh', 1, {
        'vol': 6, 'per': 4, 'spd': 5
    })
    with open('auido.mp3', 'wb') as f:
        f.write(result)
    sound = AudioSegment.from_mp3('auido.mp3')
    play(sound)
    GPIO.setmode(GPIO.BCM)
    GPIO.setup(17, GPIO.OUT)
    GPIO.output(17, GPIO.LOW)  
else:
    result = client.synthesis('   對不對不起，您的街頭暗號不對。', 'zh', 1, {
        'vol': 6, 'per': 4, 'spd': 5
    })
    with open('auido.mp3', 'wb') as f:
        f.write(result)
    sound = AudioSegment.from_mp3('auido.mp3')
    play(sound)