🎙️ آموزش ساخت دستیار صوتی شخصی با OpenAI Whisper + GPT

pip install openai
pip install speechrecognition
pip install pyaudio
pip install gtts
pip install pygame
pip install flask

import speech_recognition as sr
import openai

openai.api_key = 'YOUR_API_KEY_HERE'

def record_audio():
    recognizer = sr.Recognizer()
    microphone = sr.Microphone()
    
    with microphone as source:
        print("🎤 در حال گوش دادن...")
        recognizer.adjust_for_ambient_noise(source)
        audio = recognizer.listen(source)
        
    try:
        print("🔄 در حال پردازش...")
        with open("audio.wav", "wb") as f:
            f.write(audio.get_wav_data())
            
        with open("audio.wav", "rb") as audio_file:
            transcript = openai.Audio.transcribe(
                "whisper-1", 
                audio_file,
                language="fa"
            )
            
        return transcript["text"]
    except Exception as e:
        print(f"❌ خطا در تشخیص گفتار: {e}")
        return None

import openai

def get_gpt_response(user_input, conversation_history=[]):
    conversation_history.append({"role": "user", "content": user_input})
    
    try:
        response = openai.ChatCompletion.create(
            model="gpt-3.5-turbo",
            messages=[
                {"role": "system", "content": "You are a helpful assistant that responds in the same language as the user."},
                *conversation_history
            ],
            max_tokens=500,
            temperature=0.7
        )
        
        assistant_response = response.choices[0].message.content
        conversation_history.append({"role": "assistant", "content": assistant_response})
        
        return assistant_response, conversation_history
        
    except Exception as e:
        print(f"❌ خطا در دریافت پاسخ از GPT: {e}")
        return "متأسفانه در پردازش درخواست شما مشکلی پیش آمده است.", conversation_history

from gtts import gTTS
import pygame
import io

def text_to_speech(text, lang='fa'):
    try:
        tts = gTTS(text=text, lang=lang, slow=False)
        audio_bytes = io.BytesIO()
        tts.write_to_fp(audio_bytes)
        audio_bytes.seek(0)
        
        pygame.mixer.init()
        pygame.mixer.music.load(audio_bytes)
        pygame.mixer.music.play()
        
        while pygame.mixer.music.get_busy():
            pygame.time.Clock().tick(10)
            
    except Exception as e:
        print(f"❌ خطا در تبدیل متن به گفتار: {e}")

from speech_to_text import record_audio
from text_to_response import get_gpt_response
from text_to_speech import text_to_speech

class VoiceAssistant:
    def __init__(self):
        self.conversation_history = []
        self.is_listening = False
        
    def start_listening(self):
        self.is_listening = True
        print("🎙️ دستیار صوتی فعال شد. برای خروج بگویید 'خداحافظ'")
        
        while self.is_listening:
            user_text = record_audio()
            
            if user_text:
                print(f"👤 شما: {user_text}")
                
                if "خداحافظ" in user_text.lower() or "خدا حافظ" in user_text.lower():
                    self.stop_listening()
                    break
                
                response, self.conversation_history = get_gpt_response(user_text, self.conversation_history)
                print(f"🤖 دستیار: {response}")
                text_to_speech(response)
                
    def stop_listening(self):
        self.is_listening = False
        print("👋 دستیار صوتی غیرفعال شد.")

if __name__ == "__main__":
    assistant = VoiceAssistant()
    assistant.start_listening()

from flask import Flask, render_template, request, jsonify
from voice_assistant import VoiceAssistant
import threading

app = Flask(__name__)
assistant = VoiceAssistant()

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/start_listening', methods=['POST'])
def start_listening():
    thread = threading.Thread(target=assistant.start_listening)
    thread.daemon = True
    thread.start()
    return jsonify({"status": "started"})

@app.route('/stop_listening', methods=['POST'])
def stop_listening():
    assistant.stop_listening()
    return jsonify({"status": "stopped"})

if __name__ == '__main__':
    app.run(debug=True)

# نصب وابستگی‌ها روی سرور اوبونتو
sudo apt update
sudo apt install python3-pip portaudio19-dev python3-pyaudio
pip3 install -r requirements.txt

# اجرا با gunicorn برای production
gunicorn --workers 4 --bind 0.0.0.0:5000 app:app