app_flask.py

###################This is the Existing CODE########################################
from flask import Flask, render_template, request, jsonify
import speech_recognition as sr
from googletrans import Translator
import requests
import os
# import pyttsx3

app = Flask(__name__)

# Initialize recognizer and translator
recognizer = sr.Recognizer()
translator = Translator()
# engine = pyttsx3.init()

# Language settings mapping
language_mapping = {
    1: ('ta-IN', 'ta', 'en'),  # Tamil
    2: ('en-US', 'en', 'en'),  # English
    3: ('hi-IN', 'hi', 'en'),  # Hindi
    4: ('ms-MY', 'ms', 'en')   # Malay
}

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

# def speak(text):
#     engine.say(text)
#     engine.runAndWait()

@app.route('/speech-to-text', methods=['POST'])
def speech_to_text():
    """Convert speech to text, translate, and query the /ask endpoint"""
    language = int(request.form.get("language", 0))

    if language not in language_mapping:
        return jsonify({"error": "Invalid language selection"}), 400

    recognition_lang, src_lang, dest_lang = language_mapping[language]

    with sr.Microphone() as source:
        print(f"Listening for {recognition_lang}...")
        recognizer.adjust_for_ambient_noise(source)
        audio = recognizer.listen(source)

        try:
            text = recognizer.recognize_google(audio, language=recognition_lang)
            print(f"Recognized: {text}")

            # Translate text
            translated = translator.translate(text, src=src_lang, dest=dest_lang)
            print(f"Translated: {translated.text}")

            # Send to /ask API
            API_KEY = os.getenv("RAG_API_KEY")

            # Hugging Face API endpoint
            url = "https://aitestingworkspace-aiagentchatup.hf.space/ask"

            # Headers with authentication
            headers = {
                "Authorization": f"Bearer {API_KEY}"
            }

            response = requests.post(url=url,data={"question": translated.text},headers=headers)

            # # Get response and speak it
            # server_response = response.json().get('answer', 'No response received.')
            # print(f"Server Response: {server_response}")
            # speak(server_response)

            return jsonify({
                "recognized_text": text,
                "translated_text": translated.text,
                "server_response": response.json()['answer']
            })

        except sr.UnknownValueError:
            return jsonify({"error": "Could not understand audio"}), 400
        except Exception as e:
            return jsonify({"error": str(e)}), 500

if __name__ == "__main__":
    app.run(host="0.0.0.0", port=5000, debug=True)