Update app.py

app.py

@@ -1,6 +1,8 @@
 from flask import Flask, render_template_string, request, jsonify
 from datetime import datetime
-import speech_recognition as sr  # Import the speech_recognition module
+import speech_recognition as sr  # Import speech recognition
+from tempfile import NamedTemporaryFile
+import os
 
 app = Flask(__name__)
 
@@ -27,11 +29,9 @@ html_code = """
             height: 100vh;
             margin: 0;
         }
-
         h1 {
             color: #333;
         }
-
         .mic-button {
             width: 80px;
             height: 80px;
@@ -47,22 +47,18 @@ html_code = """
             box-shadow: 0px 4px 6px rgba(0, 0, 0, 0.1);
             transition: background-color 0.3s;
         }
-
         .mic-button:hover {
             background-color: #0056b3;
         }
-
         .status {
             margin-top: 20px;
             font-size: 18px;
             color: #666;
         }
-
         .listening {
             color: green;
             font-weight: bold;
         }
-
         .response {
             margin-top: 20px;
             padding: 10px;
@@ -80,19 +76,15 @@ html_code = """
     <button class="mic-button" id="mic-button">🎤</button>
     <div class="status" id="status">Press the mic button to start listening...</div>
     <div class="response" id="response" style="display: none;">Response will appear here...</div>
-
     <script>
         const micButton = document.getElementById('mic-button');
         const status = document.getElementById('status');
         const response = document.getElementById('response');
-
         if (!window.MediaRecorder) {
             alert("Your browser does not support audio recording.");
         }
-
         let mediaRecorder;
         let audioChunks = [];
-
         micButton.addEventListener('click', async () => {
             navigator.mediaDevices.getUserMedia({ audio: true })
                 .then(stream => {
@@ -100,30 +92,25 @@ html_code = """
                     mediaRecorder.start();
                     status.textContent = 'Listening...';
                     status.classList.add('listening');
-
+                    audioChunks = [];
                     mediaRecorder.ondataavailable = event => {
                         audioChunks.push(event.data);
                     };
-
                     mediaRecorder.onstop = async () => {
-                        const audioBlob = new Blob(audioChunks, { type: 'audio/wav' });
+                        const audioBlob = new Blob(audioChunks, { type: 'audio/wav; codecs=LINEAR16' });
                         const formData = new FormData();
                         formData.append('audio', audioBlob);
-
                         status.textContent = 'Processing...';
                         status.classList.remove('listening');
-
                         try {
                             const result = await fetch('/process-audio', {
                                 method: 'POST',
                                 body: formData,
                             });
-
                             const data = await result.json();
                             response.textContent = data.response;
                             response.style.display = 'block';
                             status.textContent = 'Press the mic button to start listening...';
-
                             // Use browser text-to-speech
                             const utterance = new SpeechSynthesisUtterance(data.response);
                             speechSynthesis.speak(utterance);
@@ -133,7 +120,6 @@ html_code = """
                             status.textContent = 'Press the mic button to start listening...';
                         }
                     };
-
                     setTimeout(() => {
                         mediaRecorder.stop();
                     }, 5000); // Stop recording after 5 seconds
@@ -155,12 +141,17 @@ def index():
 def process_audio():
     try:
         audio_file = request.files['audio']
+        # Save the audio file temporarily
+        temp_file = NamedTemporaryFile(delete=False, suffix=".wav")
+        audio_file.save(temp_file.name)
+        
         recognizer = sr.Recognizer()
-        with sr.AudioFile(audio_file) as source:
+        with sr.AudioFile(temp_file.name) as source:
             audio_data = recognizer.record(source)
             command = recognizer.recognize_google(audio_data)
             response = process_command(command)
-            return jsonify({"response": response})
+        os.unlink(temp_file.name)  # Remove the temporary file
+        return jsonify({"response": response})
     except Exception as e:
         return jsonify({"response": f"An error occurred: {str(e)}"})