app.py

import gradio as gr
from PIL import Image, ImageDraw, ImageFont
from gtts import gTTS
from moviepy.editor import ImageClip, AudioFileClip, concatenate_videoclips
import textwrap
import os

def create_video_from_text(text):
    lines = text.split('\n')

    clips = []
    for line in lines:
        # Create an image with text
        img = Image.new('RGB', (1920, 1080), color = (73, 109, 137))  # Professional color background
        d = ImageDraw.Draw(img)
        fnt = ImageFont.truetype('/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf', 50)
       
        wrapped_text = textwrap.wrap(line, width=20)  # Adjust the width parameter as needed
        y_text=50
        for line1 in wrapped_text:
            bbox = d.textbbox((0, 0), line1, font=fnt)
            textwidth, textheight = bbox[2], bbox[3]
            x= (img.width - textwidth) /2
            d.text((x, y_text), line1, font=fnt, fill=(255, 255, 255))  # White text color
            y_text += textheight
        img.save('text.png')

        # Convert text to speech
        speech = gTTS(text=line, lang='en', slow=False)
        speech.save("text.mp3")

        # Create a video clip from the image
        clip = ImageClip('text.png')

        # Set the duration of the video clip to the duration of the audio file
        audioclip = AudioFileClip('text.mp3')
        videoclip = clip.set_duration(audioclip.duration)

        # Add audio to the video clip
        videoclip = videoclip.set_audio(audioclip)

        clips.append(videoclip)

    # Concatenate all video clips
    final_clip = concatenate_videoclips(clips)

    # Write the result to a file
    final_clip.write_videofile("text.mp4", codec='libx264',fps=24)
    os.remove("text.png")
    os.remove("text.mp3")
    return "text.mp4"

iface = gr.Interface(fn=create_video_from_text, inputs="text", outputs=gr.Video())
if __name__ == "__main__":
    iface.launch()