Update app.py

app.py

@@ -240,6 +240,22 @@ async def generate_story_audios(story: StoryCreationDTO, base_output: str):
 
 #_______________ Concatenating the generated audios to make the final story (post-processing)_______________________
 
+from pydub import AudioSegment
+import os
+
+def ensure_wav(file_path: str) -> str:
+    """
+    Convert an MP3 (or other non-WAV) file to WAV.
+    Returns path to WAV file.
+    If already WAV, returns original path.
+    """
+    ext = os.path.splitext(file_path)[1].lower()
+    if ext != ".wav":
+        wav_path = file_path.rsplit(".", 1)[0] + ".wav"
+        AudioSegment.from_file(file_path).export(wav_path, format="wav")
+        return wav_path
+    return file_path
+
 from pydub import AudioSegment
 import asyncio
 
@@ -276,7 +292,8 @@ async def concat_story_audio(story: StoryCreationDTO, base_output: str, final_pa
             if scene.location.path:
                 sfx_file = await download_file_from_url(scene.location.path)
                 if sfx_file:
-                    sfx_audio = AudioSegment.from_wav(sfx_file)
+                    sfx_file_wav = ensure_wav(sfx_file)
+                    sfx_audio = AudioSegment.from_wav(sfx_file_wav)
                     scene_audio = scene_audio.overlay(sfx_audio)
                     os.remove(sfx_file)
                 else:
@@ -286,7 +303,8 @@ async def concat_story_audio(story: StoryCreationDTO, base_output: str, final_pa
             if scene.bgMusic and scene.bgMusic.musicPath:
                 bg_url = scene.bgMusic.musicPath
                 bg_file = await download_file_from_url(bg_url)
-                bg_audio = AudioSegment.from_wav(bg_file)
+                bg_file_wav = ensure_wav(bg_file)
+                bg_audio = AudioSegment.from_wav(bg_file_wav)
 
                 # Adjust volume
                 bg_audio = bg_audio - (1 - scene.bgMusic.volume) * 30  # approximate