description

app.py

@@ -140,7 +140,7 @@ with gr.Blocks(css=css) as block:
             <li>Specify the name of a male speaker (Jerry, Thomas) or female speaker (Talia, Elisabeth) for consistent voices</li>
             <li>The model can generate in a range of emotions, including: "happy", "confused", "default" (meaning no particular emotion conveyed), "laughing", "sad", "whisper", "emphasis"</li>
             <li>Punctuation can be used to control the prosody of the generations, e.g. use commas to add small breaks in speech</li>
-            <li>Wrap words in asterisk to emphasise them (e.g. `*Remember*` in the example below)</li>
+            <li>To emphasise particular words, wrap them in asterisk (e.g. *you* in the example above) and include "emphasis" in the prompt</li>
         </ul>
         </p>
         """