File size: 2,674 Bytes
d436a36 |
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 |
'''
Created By Lewis Kamau Kimaru
https://towardsdev.com/building-a-voice-assistant-using-openai-api-and-flask-by-chatgpt-9f90a430b242
https://github.com/prathmeshChaudhari05/Voice-Assistant-Flask
August 2023
'''
from flask import Flask, render_template, request, redirect, url_for, send_from_directory
from playsound import playsound
import speech_recognition as sr
from pyngrok import ngrok
from gtts import gTTS
import openai
import os
app = Flask(__name__)
# Set your ngrok authtoken
#ngrok.set_auth_token("2UAhCqf5zP0cCgJzeadNANkbIqx_7ZJvhkDSNWccqMX2hyxXP")
ngrok.set_auth_token("2S6xeFEoSVFWr2egtDRcqgeUtSx_2juefHFkEW6nGbpRHS37W")
#ngrok.set_auth_token("2UAmdjHdAFV9x84TdyEknIfNhYk_4Ye8n4YK7ZhfCMob3yPBh")
#ngrok.set_auth_token("2UAqm26HuWiWvQjzK58xYufSGpy_6tStKSyLLyR9f7pcezh6R")
#ngrok.set_auth_token("2UGQqzZoI3bx7SSk8H4wuFC3iaC_2WniWyNAsW5fd2rFyKVq1")
#ngrok.set_auth_token("2UISOtStHwytO70NQK38dFhS1at_5opQaXnoQCKeyhEe4qfT2")
# Set up OpenAI API credentials
openai.api_key = 'YOUR_API_KEY'
html_content = """
<!DOCTYPE html>
<html>
<head>
<title>Voice Assistant</title>
</head>
<body>
<h1>Voice Assistant</h1>
<form method="POST">
<button type="submit">Ask me something!</button>
</form>
<audio controls>
<source src="{{ url_for('static', filename='response.mp3') }}" type="audio/mpeg">
</audio>
</body>
</html>
"""
@app.route('/')
def home():
return html_content
def handle_form():
r = sr.Recognizer()
with sr.Microphone() as source:
print("Listening...")
audio = r.listen(source)
try:
result = r.recognize_google(audio)
print("result2:")
print(r.recognize_google(audio, show_all=True))
response = openai.Completion.create(
engine="davinci",
prompt=result,
max_tokens=60,
n=1,
stop=None,
temperature=0.5,
)
if response.choices:
tts = gTTS(text=response.choices[0].text, lang='en')
else:
tts = gTTS(text="I'm sorry, I didn't understand what you said", lang='en')
filename = 'response.mp3'
tts.save(filename)
playsound(filename)
os.remove(filename)
except sr.UnknownValueError:
print("Google Speech Recognition could not understand audio")
except sr.RequestError as e:
print("Could not request results from Google Speech Recognition service; {0}".format(e))
return html_content
@app.route('/', methods=['POST'])
def submit_textarea():
return handle_form()
ngrok_tunnel = ngrok.connect(7860)
public_url = ngrok_tunnel.public_url
print('\nPublic URL✅:', public_url)
print("\nFlask APP starting .......\n") |