Update app.py

app.py

@@ -1,7 +1,15 @@
 from flask import Flask, render_template, request, jsonify
+import os
+from werkzeug.utils import secure_filename
+from pydub import AudioSegment
 import speech_recognition as sr
 
 app = Flask(__name__)
+UPLOAD_FOLDER = 'uploads'
+app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
+
+if not os.path.exists(UPLOAD_FOLDER):
+    os.makedirs(UPLOAD_FOLDER)
 
 @app.route('/')
 def index():
@@ -16,25 +24,36 @@ def send_message():
 def echo_response(user_input):
     return user_input
 
-@app.route('/process_audio', methods=['POST'])
-def process_audio():
-    if 'audio' not in request.files:
-        return "No audio file provided", 400
-
-    audio_file = request.files['audio']
+def respond(audio_path):
     recognizer = sr.Recognizer()
+    audio = AudioSegment.from_file(audio_path)
+    audio.export("temp.wav", format="wav")
+    with sr.AudioFile("temp.wav") as source:
+        audio_data = recognizer.record(source)
+        text = recognizer.recognize_google(audio_data)
+    os.remove("temp.wav")
+    return text
+
+@app.route('/upload', methods=['POST'])
+def upload_file():
+    if 'file' not in request.files:
+        return jsonify({'error': 'No file part'})
+    
+    file = request.files['file']
+    if file.filename == '':
+        return jsonify({'error': 'No selected file'})
+    
+    filename = secure_filename(file.filename)
+    file_path = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+    file.save(file_path)
+    
+    # Process the audio file and get the response text
+    response_text = respond(file_path)
     
-    with sr.AudioFile(audio_file) as source:
-        audio = recognizer.record(source)
+    # Remove the audio file after processing
+    os.remove(file_path)
     
-    try:
-        text = recognizer.recognize_google(audio)
-        print("Transcribed Text:", text)
-        return text
-    except sr.UnknownValueError:
-        return "Could not understand audio", 400
-    except sr.RequestError as e:
-        return f"Could not request results from Google Speech Recognition service; {e}", 500
+    return jsonify({'text': response_text})
 
 if __name__ == '__main__':
     app.run(host="0.0.0.0", port=7860)