Update app.py

app.py

@@ -6,13 +6,14 @@ import os
 from typing import Dict, Tuple
 from collections import defaultdict
 
-async def text_to_speech(text: str, voice: str, rate: float, volume: float) -> str:
+async def text_to_speech(text: str, voice: str, rate: float, volume: float, pitch: float) -> str:
     output_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
     communicate = edge_tts.Communicate(
         text,
         voice,
-        rate=f"{'+' if rate >= 0 else ''}{rate}%", 
-        volume=f"+{volume}%" 
+        rate=f"{'+' if rate >= 0 else ''}{rate}%",
+        volume=f"+{volume}%",
+        pitch=f"{'+' if pitch >= 0 else ''}{pitch}Hz"
     )
     await communicate.save(output_file.name)
     return output_file.name
@@ -29,11 +30,11 @@ def process_voices(voices: Dict[str, Dict]) -> Dict[str, Dict[str, str]]:
         processed_voices[language][speaker_name] = full_name
     return dict(processed_voices)
 
-async def generate_speech(text_input, selected_language, selected_speaker, rate, volume, processed_voices):
+async def generate_speech(text_input, selected_language, selected_speaker, rate, volume, pitch, processed_voices):
     if not text_input:
         return "Por favor, introduce un texto."
     selected_voice = processed_voices[selected_language][selected_speaker]
-    output_file = await text_to_speech(text_input, selected_voice, rate, volume)
+    output_file = await text_to_speech(text_input, selected_voice, rate, volume, pitch)
     return output_file
 
 async def main():
@@ -53,7 +54,7 @@ async def main():
         with gr.Row():
             # Idiomas filtrados y "es-US" como predeterminado
             selected_language = gr.Dropdown(filtered_languages, label="Selecciona el idioma:", value="es-US") 
-            
+
             # Obtener la lista de hablantes para "es-US"
             initial_speakers = list(processed_voices["es-US"].keys())
             # Seleccionar "Alonso" si está disponible, de lo contrario, el primer hablante de la lista
@@ -63,6 +64,7 @@ async def main():
         with gr.Row():
             rate_slider = gr.Slider(minimum=-20, maximum=20, value=0, step=1, label="Velocidad (%)")
             volume_slider = gr.Slider(minimum=0, maximum=100, value=0, step=1, label="Volumen (%)")
+            pitch_slider = gr.Slider(minimum=-20, maximum=20, value=0, step=1, label="Tono (Hz)") 
 
         btn = gr.Button("Generar voz")
 
@@ -74,7 +76,7 @@ async def main():
 
         btn.click(
             generate_speech, 
-            inputs=[text_input, selected_language, selected_speaker, rate_slider, volume_slider, gr.State(processed_voices)],
+            inputs=[text_input, selected_language, selected_speaker, rate_slider, volume_slider, pitch_slider, gr.State(processed_voices)],
             outputs=audio_output
         )