AlexaCHIP/main.py at master · jitto/AlexaCHIP · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
#!/usr/bin/python
import time
import alsaaudio
import wave
import os
import random
import os
from creds import *
import requests
import json
import re
from memcache import Client
import wave


recorded = False
filename = '/sys/class/gpio/gpio409/value'
with open(filename, "r") as f:
	last = f.read()
audio = ""


#Memcache Setup
servers = ["127.0.0.1:11211"]
mc = Client(servers, debug=1)

def gettoken():
	token = mc.get("access_token")
	refresh = refresh_token
	if token:
		return token
	elif refresh:
		payload = {"client_id" : Client_ID, "client_secret" : Client_Secret, "refresh_token" : refresh, "grant_type" : "refresh_token", }
		url = "https://api.amazon.com/auth/o2/token"
		r = requests.post(url, data = payload)
		resp = json.loads(r.text)
		mc.set("access_token", resp['access_token'], 3570)
		return resp['access_token']
	else:
		return False


def play(f):
    device = alsaaudio.PCM()
    device.setchannels(f.getnchannels())
    device.setrate(f.getframerate())
    if f.getsampwidth() == 1:
        device.setformat(alsaaudio.PCM_FORMAT_U8)
    # Otherwise we assume signed data, little endian
    elif f.getsampwidth() == 2:
        device.setformat(alsaaudio.PCM_FORMAT_S16_LE)
    elif f.getsampwidth() == 3:
        device.setformat(alsaaudio.PCM_FORMAT_S24_LE)
    elif f.getsampwidth() == 4:
        device.setformat(alsaaudio.PCM_FORMAT_S32_LE)
    else:
        raise ValueError('Unsupported format')
    device.setperiodsize(320)
    data = f.readframes(320)
    while data:
        # Read data from stdin
        device.write(data)
        data = f.readframes(320)


def alexa():
	url = 'https://access-alexa-na.amazon.com/v1/avs/speechrecognizer/recognize'
	headers = {'Authorization' : 'Bearer %s' % gettoken()}
	d = {
   		"messageHeader": {
       		"deviceContext": [
           		{
               		"name": "playbackState",
               		"namespace": "AudioPlayer",
               		"payload": {
                   		"streamId": "",
        			   	"offsetInMilliseconds": "0",
                   		"playerActivity": "IDLE"
               		}
           		}
       		]
		},
   		"messageBody": {
       		"profile": "alexa-close-talk",
       		"locale": "en-us",
       		"format": "audio/L16; rate=16000; channels=1"
   		}
	}
	with open('recording.wav', 'rb') as inf:
		files = [
				('file', ('request', json.dumps(d), 'application/json; charset=UTF-8')),
				('file', ('audio', inf, 'audio/L16; rate=16000; channels=1'))
			]
		r = requests.post(url, headers=headers, files=files)
	for v in r.headers['content-type'].split(";"):
		if re.match('.*boundary.*', v):
			boundary =  v.split("=")[1]
	data = r.content.split(boundary.encode('utf-8'))
	for d in data:
		if (len(d) >= 1024):
			audio = d.split(b'\r\n\r\n')[1]
	with open("response.mp3", 'wb') as f:
		f.write(audio)
	os.system('mpg321 -q 1sec.mp3 response.mp3')


token = gettoken()
os.system('mpg321 -q 1sec.mp3 hello.mp3')
while True:
	with open(filename, "r") as f:
		val = f.read().strip('\n')
	if val != last:
		last = val
		if val == '1' and recorded == True:
			wf = wave.open('record.wav', 'wb')
			wf.setnchannels(1)
			wf.setsampwidth(2)
			wf.setframerate(44100)
			wf.writeframes(audio)
			wf.close()
			os.system('mplayer -ao pcm:fast:waveheader:file=recording.wav -srate 16000 -vo null -vc null record.wav')
			inp = None
			alexa()
		elif val == '0':
			inp = alsaaudio.PCM(alsaaudio.PCM_CAPTURE, alsaaudio.PCM_NORMAL)
			inp.setchannels(1)
			inp.setrate(44100)
			inp.setformat(alsaaudio.PCM_FORMAT_S16_LE)
			inp.setperiodsize(500)
			audio = b""
			with wave.open('beep.wav', 'rb') as f:
				play(f)
			l, data = inp.read()
			if l:
				audio += data
			recorded = True
	elif val == '0':
		l, data = inp.read()
		if l:
			audio += data