Update app.py

app.py

@@ -26,39 +26,45 @@ def process_audio(audio: tuple, state: AppState):
     state.pause_detected = pause_detected
 
     if state.pause_detected:
-        return gr.Audio(recording=False), state
+        return gr.Audio(recording=False), state  # Stop recording
     return None, state
 
 # Generate response based on input type (text or audio)
 def response(input_data, state: AppState, input_type: str):
     if input_type == "text":
-        state.conversation.append({"role": "user", "content": input_data})
-        bot_response = f"Echo: {input_data}"
+        # Ensure text input is handled correctly
+        user_message = input_data.strip()  # Prevent errors from empty inputs
+        if not user_message:
+            return "Please enter a valid message.", state
+
+        state.conversation.append({"role": "user", "content": user_message})
+        bot_response = f"Echo: {user_message}"  # Simulated bot response
         state.conversation.append({"role": "assistant", "content": bot_response})
         return bot_response, state
 
-    if not state.pause_detected:
-        return None, state
+    if input_type == "audio" and state.pause_detected:
+        # Convert audio to WAV and store in conversation history
+        audio_buffer = io.BytesIO()
+        segment = AudioSegment(
+            state.stream.tobytes(),
+            frame_rate=state.sampling_rate,
+            sample_width=state.stream.dtype.itemsize,
+            channels=1 if len(state.stream.shape) == 1 else state.stream.shape[1]
+        )
+        segment.export(audio_buffer, format="wav")
 
-    audio_buffer = io.BytesIO()
-    segment = AudioSegment(
-        state.stream.tobytes(),
-        frame_rate=state.sampling_rate,
-        sample_width=state.stream.dtype.itemsize,
-        channels=1 if len(state.stream.shape) == 1 else state.stream.shape[1]
-    )
-    segment.export(audio_buffer, format="wav")
+        with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as f:
+            f.write(audio_buffer.getvalue())
+        state.conversation.append({"role": "user", "content": {"path": f.name, "mime_type": "audio/wav"}})
 
-    with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as f:
-        f.write(audio_buffer.getvalue())
-    state.conversation.append({"role": "user", "content": {"path": f.name, "mime_type": "audio/wav"}})
+        chatbot_response = b"Simulated response audio content"
+        with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as f:
+            f.write(chatbot_response)
+        state.conversation.append({"role": "assistant", "content": {"path": f.name, "mime_type": "audio/mp3"}})
 
-    chatbot_response = b"Simulated response audio content"
-    with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as f:
-        f.write(chatbot_response)
-    state.conversation.append({"role": "assistant", "content": {"path": f.name, "mime_type": "audio/mp3"}})
+        yield None, state
 
-    yield None, state
+    return None, state  # Handle unexpected input cases gracefully
 
 # Start recording audio input
 def start_recording_user(state: AppState):
@@ -69,7 +75,7 @@ def start_recording_user(state: AppState):
 with gr.Blocks() as demo:
     with gr.Row():
         with gr.Column():
-            input_audio = gr.Audio(label="Input Audio", type="numpy")  # No 'source' argument
+            input_audio = gr.Audio(label="Input Audio", type="numpy")
             text_input = gr.Textbox(label="Text Input", placeholder="Type your message here...")
         with gr.Column():
             chatbot = gr.Chatbot(label="Conversation", type="messages")