Update app.py

app.py

@@ -3,11 +3,16 @@ import edge_tts
 import asyncio
 import tempfile
 import os
+from pydub import AudioSegment
+from pydub.playback import play
+import math
 
+# Función para obtener las voces disponibles
 async def get_voices():
     voices = await edge_tts.list_voices()
     return {f"{v['ShortName']} - {v['Locale']} ({v['Gender']})": v['ShortName'] for v in voices}
 
+# Función principal de conversión de texto a voz
 async def text_to_speech(text, voice, rate, pitch):
     if not text.strip():
         return None, "Please enter text to convert."
@@ -23,11 +28,49 @@ async def text_to_speech(text, voice, rate, pitch):
         await communicate.save(tmp_path)
     return tmp_path, None
 
-async def tts_interface(text, voice, rate, pitch):
-    audio, warning = await text_to_speech(text, voice, rate, pitch)
+# Función para agregar el fondo musical al speech
+def add_background_music(speech_file, background_music_file, output_file):
+    # Cargar los archivos de audio
+    speech = AudioSegment.from_mp3(speech_file)
+    background_music = AudioSegment.from_mp3(background_music_file)
+
+    # Ajustar el volumen del fondo musical al 15%
+    background_music = background_music - 16  # Reducción aproximada para 15%
+
+    # Repetir el fondo musical si es más corto que el speech
+    if len(background_music) < len(speech):
+        repetitions = math.ceil(len(speech) / len(background_music))
+        background_music = background_music * repetitions
+
+    # Cortar el fondo musical para que coincida con la duración del speech
+    background_music = background_music[:len(speech)]
+
+    # Superponer el speech y el fondo musical
+    final_audio = speech.overlay(background_music)
+
+    # Exportar el audio resultante
+    final_audio.export(output_file, format="mp3")
+    print(f"Archivo generado exitosamente: {output_file}")
+
+# Interfaz Gradio
+async def tts_interface(text, voice, rate, pitch, background_music):
+    # Generar el speech
+    speech_file, warning = await text_to_speech(text, voice, rate, pitch)
     if warning:
-        return audio, gr.Warning(warning)
-    return audio, None
+        return None, None, gr.Warning(warning)
+    
+    # Verificar si se proporcionó un archivo de fondo musical
+    if background_music is None or background_music == "":
+        return speech_file, None, None
+    
+    # Agregar el fondo musical
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
+        output_file = tmp_file.name
+        add_background_music(speech_file, background_music, output_file)
+    
+    # Eliminar el archivo temporal del speech original
+    os.remove(speech_file)
+    return output_file, None, None
 
 async def create_demo():
     voices = await get_voices()
@@ -55,10 +98,12 @@ async def create_demo():
             gr.Textbox(label="Input Text", lines=5),
             gr.Dropdown(choices=[""] + list(voices.keys()), label="Select Voice", value=""),
             gr.Slider(minimum=-50, maximum=50, value=0, label="Speech Rate Adjustment (%)", step=1),
-            gr.Slider(minimum=-20, maximum=20, value=0, label="Pitch Adjustment (Hz)", step=1)
+            gr.Slider(minimum=-20, maximum=20, value=0, label="Pitch Adjustment (Hz)", step=1),
+            gr.Audio(label="Background Music", type="filepath", optional=True)
         ],
         outputs=[
             gr.Audio(label="Generated Audio", type="filepath"),
+            gr.Image(label="Visualization", visible=False),
             gr.Markdown(label="Warning", visible=False)
         ],
         title="Edge TTS Text-to-Speech",
@@ -76,4 +121,4 @@ async def main():
     demo.launch(show_api=False)
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    asyncio.run(main())