Update app.py

app.py

@@ -200,7 +200,7 @@ with gr.Blocks() as demo:
             ### <center>🤗 - Powered by [Bark](https://huggingface.co/spaces/suno/bark) and [YourTTS](https://github.com/Edresson/YourTTS). Inspired by [bark-webui](https://github.com/makawy7/bark-webui).</center>
             1. You can duplicate and use it with a GPU: <a href="https://huggingface.co/spaces/{os.getenv('SPACE_ID')}?duplicate=true"><img style="display: inline; margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space" /></a>
             2. First use Bark to generate audio from text and then use YourTTS to get new audio in a custom voice you like. Easy to use!
-            
+            3. For voice cloning, longer reference audio (~90s) will generally lead to better quality of the cloned speech. Also, make sure the input audio generated by Bark is not too short.
         """
     )
     
@@ -240,13 +240,13 @@ with gr.Blocks() as demo:
     btn.click(voice_conversion, [inp5, inp6, inp7], [out2])
   
     gr.Markdown(
-            """ ### <center>NOTE: Please do not generate any audio that is potentially harmful to any person or organization.</center>
+            """ ### <center>NOTE: Please do not generate any audio that is potentially harmful to any person or organization❗</center>
                         
         """
     )
     gr.Markdown(
             """ 
-## 😄 - You may also apply [VoiceFixer](https://huggingface.co/spaces/Kevin676/VoiceFixer) to the generated audio in order to enhance the speech.
+### <center>😄 - You may also apply [VoiceFixer](https://huggingface.co/spaces/Kevin676/VoiceFixer) to the generated audio in order to enhance the speech.</center>
 ## 🌎 Foreign Language
 Bark supports various languages out-of-the-box and automatically determines language from input text. \
 When prompted with code-switched text, Bark will even attempt to employ the native accent for the respective languages in the same voice.