Update main.py

main.py

@@ -203,25 +203,17 @@ with gr.Blocks() as demo:
     gr.Markdown(description)
     with gr.Tabs():
         with gr.TabItem("Text - Audio"):
-            text_to_audio_interface = gr.Interface(
-                fn=infer_text_to_audio_gr,
-                inputs=gr.Textbox(label="Input Text"),
-                outputs=gr.Audio(label="Audio Answer"),
-                title="T2S",
-                description="Model in text to audio mode",
-                allow_flagging='never',
-            )
-            text_to_audio_interface.render()
+            gr.Markdown("### Text-to-Speech (T2S) Mode")
+            input_text = gr.Textbox(label="Input Text")
+            output_audio = gr.Audio(label="Audio Answer")
+            generate_button = gr.Button("Generate")
+            generate_button.click(infer_text_to_audio, inputs=input_text, outputs=output_audio)
         with gr.TabItem("Audio - Text"):
-            audio_to_text_interface = gr.Interface(
-                fn=infer_audio_to_text_gr,
-                inputs=gr.Audio(type="filepath", label="Input Audio"),
-                outputs=gr.Textbox(label="Text Answer"),
-                title="S2T",
-                description="Model in audio to text mode",
-                allow_flagging='never'
-            )
-            audio_to_text_interface.render()
+            gr.Markdown("### Speech-to-Text (S2T) Mode")
+            input_audio = gr.Audio(type="filepath", label="Input Audio")
+            output_text = gr.Textbox(label="Text Answer")
+            generate_button = gr.Button("Generate")
+            generate_button.click(infer_audio_to_text, inputs=input_audio, outputs=output_text)
 
 # Launch the demo
 demo.launch(share=True)