Create app.py

app.py

@@ -0,0 +1,62 @@
+import streamlit as st
+from transformers import pipeline
+from PIL import Image, ImageDraw, ImageFont
+import moviepy.editor as mpe
+import tempfile
+import os
+
+# Load TTS model
+tts_model = pipeline("text-to-speech", model="facebook/fastspeech2-en-ljspeech")
+
+def generate_audio(text, output_path):
+    tts = tts_model(text)
+    with open(output_path, "wb") as f:
+        f.write(tts[0]["waveform"])
+
+def generate_images(text, output_folder, num_images=5):
+    if not os.path.exists(output_folder):
+        os.makedirs(output_folder)
+
+    words = text.split()
+    chunk_size = max(1, len(words) // num_images)
+    chunks = [words[i:i + chunk_size] for i in range(0, len(words), chunk_size)]
+    
+    for i, chunk in enumerate(chunks):
+        image = Image.new("RGB", (1280, 720), color=(255, 255, 255))
+        draw = ImageDraw.Draw(image)
+        font = ImageFont.load_default()
+        text = " ".join(chunk)
+        draw.text((10, 360), text, fill=(0, 0, 0), font=font)
+        image.save(os.path.join(output_folder, f"frame_{i:03d}.png"))
+
+def create_video(image_folder, audio_path, output_path):
+    image_files = [os.path.join(image_folder, img) for img in sorted(os.listdir(image_folder)) if img.endswith(".png")]
+    clips = [mpe.ImageClip(img).set_duration(2) for img in image_files]
+    video = mpe.concatenate_videoclips(clips, method="compose")
+    audio = mpe.AudioFileClip(audio_path)
+    video = video.set_audio(audio)
+    video.write_videofile(output_path, fps=24)
+
+def main():
+    st.title("Text to Video Generator")
+
+    text_input = st.text_area("Enter the text to generate video:", "")
+
+    if st.button("Generate Video"):
+        if text_input:
+            with tempfile.TemporaryDirectory() as temp_dir:
+                audio_path = os.path.join(temp_dir, "audio.wav")
+                image_folder = os.path.join(temp_dir, "images")
+                video_path = os.path.join(temp_dir, "video.mp4")
+
+                generate_audio(text_input, audio_path)
+                generate_images(text_input, image_folder)
+                create_video(image_folder, audio_path, video_path)
+
+                with open(video_path, "rb") as video_file:
+                    st.video(video_file.read(), format="video/mp4")
+        else:
+            st.error("Please enter some text.")
+
+if __name__ == "__main__":
+    main()