Update app.py

app.py

@@ -1,74 +1,47 @@
-import os
-import time
-import speech_recognition as sr
-import pyttsx3
 from flask import Flask, render_template, request, jsonify
+import speech_recognition as sr
+from gtts import gTTS
+import os
+import tempfile
 
 app = Flask(__name__)
 
-# Initialize the recognizer and text-to-speech engine
-recognizer = sr.Recognizer()
-engine = pyttsx3.init()
-
-# Temporary file to store the audio recording
-audio_file_path = "temporary_audio.wav"
-
-# Function to record audio from the microphone
-def record_audio():
-    with sr.Microphone() as source:
-        print("Please start speaking...")
-        recognizer.adjust_for_ambient_noise(source)  # Adjusts for ambient noise before listening
-        audio = recognizer.listen(source)
-        print("Recording completed.")
-        return audio
-
-# Function to transcribe speech to text
-def transcribe_audio(audio):
-    try:
-        print("Recognizing...")
-        text = recognizer.recognize_google(audio)  # Using Google Speech Recognition API
-        return text
-    except sr.UnknownValueError:
-        return "Sorry, I could not understand the audio."
-    except sr.RequestError:
-        return "Sorry, there was an error with the speech recognition service."
-
-# Function to convert text to speech
+# Function to convert text to speech using gTTS
 def speak_text(text):
-    engine.say(text)
-    engine.runAndWait()
+    tts = gTTS(text=text, lang='en')
+    temp_file = tempfile.NamedTemporaryFile(delete=False)
+    tts.save(temp_file.name)
+    os.system(f"mpg321 {temp_file.name}")  # Plays the saved audio file
+    os.remove(temp_file.name)  # Deletes the file after playing
 
-@app.route('/')
-def index():
-    return render_template('index.html')
+# Initialize recognizer
+recognizer = sr.Recognizer()
 
-@app.route('/start_recording', methods=['POST'])
+# Route to handle speech input and process it
+@app.route("/start_recording", methods=["POST"])
 def start_recording():
-    try:
-        # Record the audio
-        audio = record_audio()
-        
-        # Transcribe the audio
-        transcribed_text = transcribe_audio(audio)
+    with sr.Microphone() as source:
+        recognizer.adjust_for_ambient_noise(source)
+        print("Listening for speech... Please speak.")
+        audio_data = recognizer.listen(source)
         
-        # Speak the transcribed text
-        speak_text(transcribed_text)
+        try:
+            # Recognize speech and convert to text
+            print("Recognizing speech...")
+            text = recognizer.recognize_google(audio_data)
+            print(f"Recognized text: {text}")
+            # Respond with text-to-speech
+            speak_text(f"You said: {text}")
+            return jsonify({"text": text, "status": "success"})
         
-        # Return the transcription and status
-        return jsonify({'status': 'success', 'transcription': transcribed_text})
-    except Exception as e:
-        return jsonify({'status': 'error', 'message': str(e)})
+        except sr.UnknownValueError:
+            return jsonify({"error": "Could not understand the audio", "status": "error"})
+        except sr.RequestError:
+            return jsonify({"error": "Could not request results from Google Speech Recognition service", "status": "error"})
 
-@app.route('/stop_recording', methods=['POST'])
-def stop_recording():
-    try:
-        # If there was any temporary file for the recording, we can delete it (not necessary in real-time recording)
-        if os.path.exists(audio_file_path):
-            os.remove(audio_file_path)
-        
-        return jsonify({'status': 'success', 'message': 'Recording stopped and temporary files removed.'})
-    except Exception as e:
-        return jsonify({'status': 'error', 'message': str(e)})
+@app.route("/")
+def index():
+    return render_template("index.html")
 
 if __name__ == "__main__":
     app.run(debug=True)