Update app.py

app.py

@@ -613,9 +613,11 @@ def generate_story_and_speech(input_text, chatbot_role):
         synthesized_speech = generate_speech_for_sentence(history_tuples, chatbot_role, story_text) 
         if synthesized_speech:
             # Access the BytesIO object containing the WAV file and extract bytes
-            speech_audio = synthesized_speech[1]["value"] if return_as_byte else synthesized_speech[1].data.getvalue()
+            speech_audio_bytes = synthesized_speech[1]["value"]  # Assume speech audio is always in bytearray format
+            
             # Convert the speech audio bytes to base64 for JSON serialization
-            speech_audio_base64 = base64.b64encode(speech_audio).decode('utf8')
+            speech_audio_base64 = base64.b64encode(speech_audio_bytes).decode('utf8')
+
 
             return {"text": story_text.strip(), "audio": speech_audio_base64}
     else: