Update Modules/Generate_Speech.py

Modules/Generate_Speech.py

@@ -651,18 +651,18 @@ def build_interface() -> gr.Interface:
     return gr.Interface(
         fn=Generate_Speech,
         inputs=[
-            gr.Textbox(label="Text", placeholder="Type text to synthesize…", lines=4),
-            gr.Dropdown(label="Model", choices=["Supertonic", "Kokoro"], value="Supertonic"),
-            gr.Slider(minimum=0.5, maximum=2.0, value=1.3, step=0.1, label="Speed"),
-            gr.Slider(minimum=1, maximum=50, value=5, step=1, label="Steps", info="Supertonic only"),
+            gr.Textbox(label="Text", placeholder="Type text to synthesize…", lines=4, info="The text to synthesize (English)"),
+            gr.Dropdown(label="Model", choices=["Supertonic", "Kokoro"], value="Supertonic", info="The TTS model to use"),
+            gr.Slider(minimum=0.5, maximum=2.0, value=1.3, step=0.1, label="Speed", info="Speech speed multiplier (1.0 = normal)"),
+            gr.Slider(minimum=1, maximum=50, value=5, step=1, label="Steps", info="Supertonic only: Diffusion steps (1-50)"),
             gr.Dropdown(
                 label="Voice",
                 choices=all_voices,
                 value="F1",
                 info="Select voice (F1/F2/M1/M2 for Supertonic, others for Kokoro)",
             ),
-            gr.Slider(minimum=0.0, maximum=2.0, value=0.3, step=0.1, label="Silence Duration", info="Supertonic only"),
-            gr.Slider(minimum=50, maximum=1000, value=300, step=10, label="Max Chunk Size", info="Supertonic only"),
+            gr.Slider(minimum=0.0, maximum=2.0, value=0.3, step=0.1, label="Silence Duration", info="Supertonic only: Silence duration between chunks"),
+            gr.Slider(minimum=50, maximum=1000, value=300, step=10, label="Max Chunk Size", info="Supertonic only: Max text chunk length"),
         ],
         outputs=gr.Audio(label="Audio", type="filepath", format="wav"),
         title="Generate Speech",