Update app.py

app.py

@@ -1,13 +1,16 @@
+# 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
 from io import BytesIO
 from PIL import Image
 from diffusers import DiffusionPipeline
-import openai
-
-# Set your OpenAI API key
-openai.api_key = "YOUR_OPENAI_API_KEY"
+from transformers import pipeline
 
 # Use a DiffusionPipeline for text-to-image
 image_generation_pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-video-diffusion-img2vid-xt")
@@ -18,8 +21,11 @@ messages = [{"role": "system", "content": "You are a magical storyteller, creati
 # Initialize page number
 current_page = 0
 
+# Initialize Hugging Face text generation pipeline
+gpt_neo_generator = pipeline("text-generation", model="EleutherAI/gpt-neo-1.3B", device=0)  # You can adjust the device parameter based on your setup
+
 # Define the Storyteller function
-def StorytellerGPT(character, child_name, lesson_choice, tell_story, _):
+def StorytellerHuggingFace(character, child_name, lesson_choice, tell_story, _):
     global current_page
     
     # Set the characters and lesson based on user choices
@@ -28,25 +34,16 @@ def StorytellerGPT(character, child_name, lesson_choice, tell_story, _):
     
     messages.append({"role": "user", "content": tell_story})
     
-    # Generate story using OpenAI's GPT model
+    # Generate story using Hugging Face's GPT-Neo
     input_text = character_info + lesson_info + tell_story
-    story_reply = openai.Completion.create(
-        engine="text-davinci-003",  # Adjust the engine based on your preferences
-        prompt=input_text,
-        max_tokens=150,
-        n=1,
-        stop=None
-    )["choices"][0]["text"]
+    story_reply = gpt_neo_generator(input_text, max_length=150, num_return_sequences=1, no_repeat_ngram_size=2, top_k=50, top_p=0.95)[0]['generated_text']
 
     messages.append({"role": "assistant", "content": story_reply})
     
-    # Convert text to speech using Whisper API
-    # Replace "YOUR_WHISPER_API_KEY" with your actual Whisper API key
-    whisper_api_key = "YOUR_WHISPER_API_KEY"
-    tts = gTTS(text=story_reply, lang='en', slow=False, whisper_api_key=whisper_api_key)
+    # Convert text to speech using gTTS
+    tts = gTTS(text=story_reply, lang='en', slow=False)
     audio_io = BytesIO()
-    tts.save(audio_io)
-    audio_io.seek(0)
+    tts.save("/content/audio_output.mp3")
 
     # Convert text to image using DiffusionPipeline
     image_reply = image_generation_pipe(story_reply)
@@ -55,11 +52,11 @@ 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], Audio(data=audio_io.read(), autoplay=True), image_reply
+    return story_pages[current_page], "/content/audio_output.mp3", image_reply
 
 # Create the Gradio Interface with styling
 demo = gr.Interface(
-    fn=StorytellerGPT,
+    fn=StorytellerHuggingFace,
     inputs=[
         gr.Textbox("text", label="Child's Name"),
         gr.Dropdown(["unicorn", "dragon", "wizard"], label="Choose a Character"),