import gradio as gr import edge_tts import asyncio import tempfile import os # Obtener todas 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 de texto a voz async def text_to_speech(text, voice, rate, pitch): if not text.strip(): return None, gr.Warning("Por favor, introduce texto para convertir.") if not voice: return None, gr.Warning("Por favor, selecciona una voz.") voice_short_name = voice.split(" - ")[0] rate_str = f"{rate:+d}%" pitch_str = f"{pitch:+d}Hz" communicate = edge_tts.Communicate(text, voice_short_name, rate=rate_str, pitch=pitch_str) with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file: tmp_path = tmp_file.name await communicate.save(tmp_path) return tmp_path, None # Función de interfaz Gradio def tts_interface(text, voice, rate, pitch): audio, warning = asyncio.run(text_to_speech(text, voice, rate, pitch)) return audio, warning # Crear la aplicación Gradio import gradio as gr async def create_demo(): voices = await get_voices() description = """ Convierte texto en voz utilizando Microsoft Edge TTS. Ajusta la velocidad y tono de la voz: 0 es el valor predeterminado, valores positivos incrementan, valores negativos disminuyen. """ demo = gr.Interface( fn=tts_interface, inputs=[ gr.Textbox(label="Texto de Entrada", lines=5), gr.Dropdown(choices=[""] + list(voices.keys()), label="Selecciona Voz", value=""), gr.Slider(minimum=-50, maximum=50, value=0, label="Ajuste de Velocidad de la Voz (%)", step=1), gr.Slider(minimum=-20, maximum=20, value=0, label="Ajuste de Tono (Hz)", step=1) ], outputs=[ gr.Audio(label="Audio Generado", type="filepath"), gr.Markdown(label="Advertencia", visible=False) ], title="Convertidor Texto a Voz", description=description, article="", analytics_enabled=False, allow_flagging=False, submit_btn="Convertir🚀" ) return demo # Ejecutar la aplicación if __name__ == "__main__": demo = asyncio.run(create_demo()) demo.launch()