Update app.py

app.py

@@ -347,6 +347,9 @@ def vqa_answer(image, question):
     return answer, None
 
 
+# ----------------------
+# Gradio UI
+# ----------------------
 # ----------------------
 # Gradio UI
 # ----------------------
@@ -359,7 +362,7 @@ with gr.Blocks(title="BLIP Vision App") as demo:
             lang_in = gr.Dropdown(["Hindi", "French", "Spanish"], label="Translate To", value="Hindi")
         eng_out = gr.Textbox(label="English Caption")
         trans_out = gr.Textbox(label="Translated Caption")
-        audio_out = gr.Audio(label="Audio Output", type="filepath")
+        audio_out = gr.Audio(label="Audio Output", type="filepath", autoplay=True)  # 👈 added autoplay
         btn1 = gr.Button("Generate Caption, Translate & Speak")
         btn1.click(generate_caption_translate_speak, inputs=[img_in, lang_in], outputs=[eng_out, trans_out, audio_out])
 
@@ -368,7 +371,7 @@ with gr.Blocks(title="BLIP Vision App") as demo:
             img_vqa = gr.Image(type="pil", label="Upload Image")
             q_in = gr.Textbox(label="Ask a Question about the Image")
         ans_out = gr.Textbox(label="Answer")
-        beep_out = gr.Audio(label="Alert Sound", type="filepath")
+        beep_out = gr.Audio(label="Alert Sound", type="filepath", autoplay=True)  # 👈 added autoplay
         btn2 = gr.Button("Ask")
         btn2.click(vqa_answer, inputs=[img_vqa, q_in], outputs=[ans_out, beep_out])