Update app.py

app.py

@@ -11,7 +11,12 @@ audio_gen = gr.Blocks.load(name="spaces/fffiloni/audioldm-text-to-audio-generati
 def infer(image_input):
     cap = caption(image_input, fn_index=0)
     sound = audio_gen(cap, 10, 2.5, 45, 3, fn_index=0)
-    return cap, sound[1], gr.Group.update(visible=True)
+
+    FILETOCONVERT = AudioFileClip(sound[0])
+    FILETOCONVERT.write_audiofile("audio.wav")
+    FILETOCONVERT.close()
+    
+    return cap, "audio.wav", gr.Group.update(visible=True)
 
 title = """
     <div style="text-align: center; max-width: 700px; margin: 0 auto;">