Create app.py

app.py

@@ -0,0 +1,46 @@
+import gradio
+import edge_tts
+import subprocess
+
+VOICE = "ml-IN-MidhunNeural"
+
+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:
+        async for chunk in communicate.stream():
+            if chunk["type"] == "audio":
+                file.write(chunk["data"])
+            elif chunk["type"] == "WordBoundary":
+                submaker.create_sub((chunk["offset"], chunk["duration"]), chunk["text"])
+
+    with open(WEBVTT_FILE, "w", encoding="utf-8") as file:
+        file.write(submaker.generate_subs())
+
+    ffmpeg_command = [
+        "ffmpeg", 
+        "-y",  
+        "-loop", "1", 
+        "-i", "background.jpg", 
+        "-i", "output.mp3", 
+        "-vf", "subtitles=output.vtt:force_style='FontSize=24,PrimaryColour=&HFFFFFF'",
+        "-c:v", "libx264", 
+        "-c:a", "aac", 
+        "-shortest", 
+        OUTPUT_FILE
+    ]
+    subprocess.run(ffmpeg_command, check=True)
+
+    return OUTPUT_FILE
+
+interface = gradio.Interface(
+    fn=text2video,
+    inputs="text",
+    outputs=["video"],
+)
+
+interface.launch()