Update app.py

app.py

@@ -3,15 +3,16 @@ import edge_tts
 import subprocess
 
 VOICE = "ml-IN-MidhunNeural"
+VIDEO_FILE = "output.mp4"
+AUDIO_FILE = "output.mp3"
+WEBVTT_FILE = "output.vtt"
+FONT_SIZE = 40
 
 async def text2video(text):
-    OUTPUT_FILE = "output.mp4"
-    WEBVTT_FILE = "output.vtt"
-
     communicate = edge_tts.Communicate(text, VOICE)
     submaker = edge_tts.SubMaker()
 
-    with open("output.mp3", "wb") as file:
+    with open(AUDIO_FILE, "wb") as file:
         async for chunk in communicate.stream():
             if chunk["type"] == "audio":
                 file.write(chunk["data"])
@@ -26,19 +27,19 @@ async def text2video(text):
         "-y",  
         "-stream_loop", "1", 
         "-i", "background.mp4", 
-        "-i", "output.mp3", 
-        "-vf", "subtitles=output.vtt",
+        "-i", AUDIO_FILE, 
+        "-vf", f"subtitles={WEBVTT_FILE}:force_style='FontSize={FONT_SIZE}'",
         "-shortest", 
-        OUTPUT_FILE
+        VIDEO_FILE
     ]
     subprocess.run(ffmpeg_command)
 
-    return OUTPUT_FILE
+    return VIDEO_FILE
 
 interface = gradio.Interface(
     fn=text2video,
     inputs="text",
-    outputs=["video"],
+    outputs="video",
 )
 
 interface.launch()