Update app.py

app.py

@@ -1,30 +1,36 @@
 import gradio as gr
 from transformers import pipeline
-from gtts import gTTS
-from moviepy.editor import CompositeVideoClip, ImageClip, AudioFileClip, concatenate_videoclips
 from diffusers import StableDiffusionPipeline
 import torch
 from PIL import Image, ImageDraw, ImageFont
 import scipy.io.wavfile
-import random
+from TTS.api import TTS  # Coqui TTS (open source)
+from moviepy.editor import CompositeVideoClip, ImageClip, AudioFileClip, concatenate_videoclips
 
 # Load and Initialize Models
+# Use GPT-2 (open-source) for text generation
 script_generator = pipeline("text-generation", model="gpt2", truncation=True, max_length=100)
-image_generator = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16).to("cpu")
+
+# Use Stable Diffusion (open-source) for image generation
+image_generator = StableDiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1-base", torch_dtype=torch.float16).to("cpu")
+
+# Use MusicGen (open-source) for music generation
 music_generator = pipeline("text-to-audio", model="facebook/musicgen-small", device="cpu")
 
+# Use Coqui TTS (open-source) for text-to-speech
+tts = TTS(model_name="tts_models/en/ljspeech/tacotron2-DDC", progress_bar=False, gpu=False)
+
 
 # Generate Comedy Script
 def generate_comedy_script(prompt):
     script = script_generator(prompt)[0]['generated_text']
     return script
 
-# Convert Text to Speech
+# Convert Text to Speech using Coqui TTS
 def text_to_speech(script):
-    tts = gTTS(text=script, lang='en')
-    audio_file = 'output.mp3'
-    tts.save(audio_file)
-    return audio_file
+    output_audio = 'output.wav'
+    tts.tts_to_file(text=script, file_path=output_audio)
+    return output_audio
 
 # Create Images Using Stable Diffusion
 def create_images_from_script(script):
@@ -37,7 +43,7 @@ def create_images_from_script(script):
         image_paths.append(img_path)
     return image_paths
 
-# Update: Generate Fun Music Track using MusicGen
+# Generate Fun Music Track using MusicGen
 def generate_fun_music(prompt, output_music_file="fun_music.wav"):
     # Generate music based on the prompt using MusicGen
     response = music_generator(prompt)
@@ -141,3 +147,4 @@ app.launch()
 
 
 
+