Update app.py

app.py

@@ -1,80 +1,50 @@
-# 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
+import openai
+import whisper
 from PIL import Image
-from diffusers import DiffusionPipeline
-from transformers import pipeline
+from diffusers import StableDiffusionPipeline
 
-# Use a DiffusionPipeline for text-to-image
-image_generation_pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-video-diffusion-img2vid-xt")
+# Set your OpenAI API key
+openai.api_key = ""
 
-# Set the context for the storyteller
-messages = [{"role": "system", "content": "You are a magical storyteller, creating wonderful tales for kids. Make them imaginative and full of joy!"}]
+# Initialize text generation and image generation pipelines
+text_generation_pipe = openai.Completion.create
+image_generation_pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4")
 
-# Initialize page number
-current_page = 0
+# Initialize Whisper API key for text-to-speech
+whisper_api_key = ""
 
-# 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 function for generating stories and illustrations
+def generate_story_and_illustration(prompt, character_name):
+    # Generate story
+    story_text = text_generation_pipe(engine="text-davinci-003", prompt=f"Once upon a time, {character_name}... {prompt}", max_tokens=150)["choices"][0]["text"]
 
-# Define the Storyteller function
-def StorytellerHuggingFace(character, child_name, lesson_choice, tell_story, _):
-    global current_page
-    
-    # Set the characters and lesson based on user choices
-    character_info = f"Once upon a time, {child_name} met {character}. "
-    lesson_info = f"Today's lesson is about {lesson_choice}. "
-    
-    messages.append({"role": "user", "content": tell_story})
-    
-    # Generate story using Hugging Face's GPT-Neo
-    input_text = character_info + lesson_info + tell_story
-    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']
+    # Generate image based on story
+    image = image_generation_pipe(story_text)
 
-    messages.append({"role": "assistant", "content": story_reply})
-    
-    # Convert text to speech using gTTS
-    tts = gTTS(text=story_reply, lang='en', slow=False)
-    audio_io = BytesIO()
-    tts.save("/content/audio_output.mp3")
+    # Convert story text to speech using Whisper API
+    tts_result = whisper.transcribe(audio="content.flac", language="en", api_key=whisper_api_key)
+    audio_data = tts_result["segments"][0]["alternatives"][0]["text"]
 
-    # Convert text to image using DiffusionPipeline
-    image_reply = image_generation_pipe(story_reply)
-    
-    # Display the story on separate pages
-    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 text, audio data, and image
+    return story_text, audio_data, image.images[0]
 
-# Create the Gradio Interface with styling
-demo = gr.Interface(
-    fn=StorytellerHuggingFace,
+# Create Gradio interface
+interface = gr.Interface(
+    fn=generate_story_and_illustration,
     inputs=[
-        gr.Textbox("text", label="Child's Name"),
-        gr.Dropdown(["unicorn", "dragon", "wizard"], label="Choose a Character"),
-        gr.Dropdown(["kindness", "creativity", "bravery"], label="Choose a Lesson"),
-        gr.Textbox("text", label="Start the Story with"),
-        gr.Button("Next Page"),
+        gr.Textbox(label="Start your story with..."),
+        gr.Textbox(label="Give your character a name:"),
+    ],
+    outputs=[
+        gr.Textbox(label="Story"),
+        gr.Audio(label="Listen to the story"),
+        gr.Image(label="See the story come alive"),
     ],
-    outputs=["text", "audio", "image"],
-    title="📖 Storytelling Magic",
-    description="A magical storyteller app for kids! Choose characters, add your name, and select the lesson you want to learn.",
-    live=True,  # Enable live updates for CSS changes
-    css=f"""body {{
-        background-image: url('https://www.bing.com/images/create/a-castle-ai-metaverse-style/1-657576205c7146f2b7f2f8d1c552810f?id=dZs6kpD2HfmH4eojx%2bHjdA%3d%3d&view=detailv2&idpp=genimg&FORM=GCRIDP&mode=overlay');
-        background-size: cover;
-        background-position: center;
-        font-family: 'Comic Sans MS', cursive, sans-serif; /* Optional: Change the font */
-    }}""",
+    title="Storyteller Playground",
+    description="Create amazing stories with the help of AI!",
+    theme="kids",
 )
 
-# Launch the Gradio Interface
-demo.launch()
+# Launch the app on Hugging Face Spaces
+interface.launch()