Update app.py

app.py

@@ -3,10 +3,11 @@ from gtts import gTTS
 import os
 import tempfile
 import json
-import speech_recognition as sr
+import sounddevice as sd
+import queue
 import threading
-import time
-from playsound import playsound
+from scipy.io.wavfile import write
+import speech_recognition as sr
 
 # Store cart in a temporary storage
 cart = []
@@ -33,29 +34,46 @@ def generate_voice_response(text):
 def calculate_total(cart):
     return sum(menu_items[item] for item in cart)
 
-def play_audio_with_control(audio_path):
-    global playback_control
-    playback_control["stop"] = False
-    playback_control["pause"] = False
+def play_audio(audio_path):
+    import simpleaudio as sa
     try:
-        for _ in range(3):  # Retry loop in case of interruptions
-            if playback_control["stop"]:
-                break
-            playsound(audio_path)
-            break
+        playback = sa.WaveObject.from_wave_file(audio_path).play()
+        playback.wait_done()
     except Exception as e:
         print("Error playing audio:", e)
 
+# Audio recording setup
+q = queue.Queue()
+def audio_callback(indata, frames, time, status):
+    if status:
+        print(status)
+    q.put(indata.copy())
+
+def record_audio():
+    fs = 16000  # Sample rate
+    seconds = 5  # Duration
+    print("Recording...")
+    audio_data = []
+    with sd.InputStream(callback=audio_callback, samplerate=fs, channels=1):
+        for _ in range(int(fs * seconds / 1024)):
+            audio_data.append(q.get())
+    print("Recording finished.")
+    return b"".join(audio_data)
+
 def restaurant_voice_assistant():
     global cart
     recognizer = sr.Recognizer()
 
     # Continuously listen for user commands
     while True:
-        with sr.Microphone() as source:
-            print("Listening for input...")
-            try:
-                audio = recognizer.listen(source)
+        try:
+            audio_data = record_audio()
+            with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as temp_audio:
+                temp_audio.write(audio_data)
+                temp_audio_path = temp_audio.name
+
+            with sr.AudioFile(temp_audio_path) as source:
+                audio = recognizer.record(source)
                 input_text = recognizer.recognize_google(audio)
                 print("You said:", input_text)
 
@@ -99,12 +117,12 @@ def restaurant_voice_assistant():
 
                 # Generate and play audio response
                 audio_path = generate_voice_response(response)
-                threading.Thread(target=play_audio_with_control, args=(audio_path,)).start()
+                play_audio(audio_path)
 
-            except sr.UnknownValueError:
-                print("Sorry, I didn’t catch that. Could you please repeat?")
-            except Exception as e:
-                print("Error occurred:", e)
+        except sr.UnknownValueError:
+            print("Sorry, I didn’t catch that. Could you please repeat?")
+        except Exception as e:
+            print("Error occurred:", e)
 
 # Run the assistant
 threading.Thread(target=restaurant_voice_assistant).start()