Update app.py

app.py

@@ -2,6 +2,7 @@ from flask import Flask, render_template_string, request, jsonify
 from datetime import datetime
 import speech_recognition as sr  # Import speech recognition
 from tempfile import NamedTemporaryFile
+import ffmpeg
 import os
 
 app = Flask(__name__)
@@ -141,16 +142,23 @@ def index():
 def process_audio():
     try:
         audio_file = request.files['audio']
-        # Save the audio file temporarily
+        # Save the uploaded file temporarily
         temp_file = NamedTemporaryFile(delete=False, suffix=".wav")
         audio_file.save(temp_file.name)
         
+        # Convert the file to PCM WAV format if necessary
+        converted_file = NamedTemporaryFile(delete=False, suffix=".wav")
+        ffmpeg.input(temp_file.name).output(converted_file.name, acodec='pcm_s16le', ac=1, ar='16000').run(overwrite_output=True)
+
         recognizer = sr.Recognizer()
-        with sr.AudioFile(temp_file.name) as source:
+        with sr.AudioFile(converted_file.name) as source:
             audio_data = recognizer.record(source)
             command = recognizer.recognize_google(audio_data)
             response = process_command(command)
-        os.unlink(temp_file.name)  # Remove the temporary file
+
+        # Clean up temporary files
+        os.unlink(temp_file.name)
+        os.unlink(converted_file.name)
         return jsonify({"response": response})
     except Exception as e:
         return jsonify({"response": f"An error occurred: {str(e)}"})