Update app.py

app.py

@@ -753,6 +753,10 @@ def main():
                     textbox_4 = gr.TextArea(label="请输入您想合成的文本",
                                           placeholder="说点什么吧(中英皆可)...",
                                           elem_id=f"tts-input")
+                    
+                    btn_4 = gr.Button("声音克隆", variant="primary")
+                    btn_5 = gr.Button("去除噪音", variant="primary")
+                    
                     language_dropdown_4 = gr.Dropdown(choices=['auto-detect', 'English', '中文', '日本語'], value='auto-detect',
                                                     label='language', visible=False)
                     accent_dropdown_4 = gr.Dropdown(choices=['no-accent', 'English', '中文', '日本語'], value='no-accent',
@@ -761,7 +765,7 @@ def main():
                     prompt_file_4 = prompt_output_2
                 with gr.Column():
                     text_output_4 = gr.TextArea(label="Message", visible=False)
-                    audio_output_4 = gr.Audio(label="为您合成的专属语音", elem_id="tts-audio")
+                    audio_output_4 = gr.Audio(label="为您合成的专属语音", elem_id="tts-audio", interactive=False)
 
 
                     radio = gr.Radio(
@@ -793,8 +797,6 @@ def main():
                         gr.Image(label="Enhanced spectrogram", visible=False),
                     ]
                             
-                    btn_4 = gr.Button("声音克隆", variant="primary")
-                    btn_5 = gr.Button("去除噪音", variant="primary")
                     btn_4.click(infer_long_text,
                               inputs=[textbox_4, preset_dropdown_4, prompt_file_4, language_dropdown_4, accent_dropdown_4],
                               outputs=[text_output_4, audio_output_4])