Update app.py

app.py

@@ -1,9 +1,3 @@
-# Install required libraries
-!pip install gtts
-!pip install gradio
-!pip install transformers
-!pip install diffusers
-
 # Import libraries
 import gradio as gr
 from gtts import gTTS
@@ -13,7 +7,7 @@ from diffusers import DiffusionPipeline
 import openai
 
 # Set your OpenAI API key
-openai.api_key = "sk-pZv0gFbHlaKc5o3ejPgYT3BlbkFJ7DPw0d1FqJApeZTBjIqic"
+openai.api_key = "YOUR_OPENAI_API_KEY"
 
 # Use a DiffusionPipeline for text-to-image
 image_generation_pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-video-diffusion-img2vid-xt")
@@ -48,10 +42,11 @@ def StorytellerGPT(character, child_name, lesson_choice, tell_story, _):
     
     # Convert text to speech using Whisper API
     # Replace "YOUR_WHISPER_API_KEY" with your actual Whisper API key
-    whisper_api_key = "sk-pZv0gFbHlaKc5o3ejPgYT3BlbkFJ7DPw0d1FqJApeZTBjIqic"
+    whisper_api_key = "YOUR_WHISPER_API_KEY"
     tts = gTTS(text=story_reply, lang='en', slow=False, whisper_api_key=whisper_api_key)
     audio_io = BytesIO()
-    tts.save("/content/audio_output.mp3")
+    tts.save(audio_io)
+    audio_io.seek(0)
 
     # Convert text to image using DiffusionPipeline
     image_reply = image_generation_pipe(story_reply)
@@ -60,7 +55,7 @@ def StorytellerGPT(character, child_name, lesson_choice, tell_story, _):
     story_pages = story_reply.split("\n\n")  # Split the story into pages
     current_page = min(current_page, len(story_pages) - 1)  # Ensure the current_page is within bounds
     
-    return story_pages[current_page], "/content/audio_output.mp3", image_reply
+    return story_pages[current_page], Audio(data=audio_io.read(), autoplay=True), image_reply
 
 # Create the Gradio Interface with styling
 demo = gr.Interface(