Update app.py

app.py

@@ -17,13 +17,12 @@ def generate_audio(text):
     
     # Use IPythonAudio to play the audio
     audio = IPythonAudio(audio_data, rate=sampling_rate)
-    return audio
+    return audio_data, sampling_rate
 
 def launch_image_pipe(input):
     out = image_pipe(input)
     text = out[0]['generated_text']
-    audio = generate_audio(text)
-    return text, audio
+    return text
 
 def translate(input_text, source, target):
     try:
@@ -118,10 +117,12 @@ with playground:
                     img = gr.Image(type='pil')
                 with gr.Column():
                     generated_textbox = gr.Textbox(lines=2, placeholder="", label="Generated Text")
+                    generate_audio_button = gr.Button(value="Generate Audio", variant="primary")
                     audio_output = gr.Audio(label="Generated Audio")
-                    ITT_Clear_button = gr.ClearButton(components=[img, generated_textbox], value="Clear")
+                    ITT_Clear_button = gr.ClearButton(components=[img, generated_textbox, audio_output], value="Clear")
                         
             ITT_button.click(launch_image_pipe, inputs=[img], outputs=[generated_textbox, audio_output])
+            generate_audio_button.click(generate_audio, inputs=[generated_textbox], outputs=[audio_output])
         
         with gr.TabItem("Text"):
             with gr.Row():