idk

app.py

@@ -29,7 +29,7 @@ import soundfile as sf
 
 from model import get_pretrained_model, language_to_models
 
-title = "# Next-gen Kaldi: Text-to-speech (TTS)"
+title = "# Texto a Voz"
 
 description = """
 Este espacio muestra el comó convertir texto a voz con tecnologías como Piper, Kaldi, y Next-gen.
@@ -130,14 +130,12 @@ with demo:
     language_choices = list(language_to_models.keys())
 
     language_radio = gr.Radio(
-        label="Language",
         choices=language_choices,
         value=language_choices[0],
     )
 
     model_dropdown = gr.Dropdown(
         choices=language_to_models[language_choices[0]],
-        label="Select a model",
         value=language_to_models[language_choices[0]][0],
     )
 
@@ -156,6 +154,14 @@ with demo:
                 placeholder="Por favor ingresa tu texto aquí",
             )
 
+            input_sid = gr.Textbox(
+                info="Speaker ID",
+                lines=1,
+                max_lines=1,
+                value="0",
+                placeholder="Speaker ID. Valid only for mult-speaker model",
+            )
+
             input_speed = gr.Slider(
                 minimum=0.1,
                 maximum=10,
@@ -177,6 +183,7 @@ with demo:
                     language_radio,
                     model_dropdown,
                     input_text,
+                    input_sid,
                     input_speed,
                 ],
                 outputs=[
@@ -191,6 +198,7 @@ with demo:
                 language_radio,
                 model_dropdown,
                 input_text,
+                input_sid,
                 input_speed,
             ],
             outputs=[