Spaces:
Sleeping
Sleeping
File size: 8,450 Bytes
8b274aa 15e8c2d bafc5cd 15e8c2d b82e6a6 15e8c2d 6d66777 b82e6a6 15e8c2d b82e6a6 1829fd6 b82e6a6 1829fd6 b82e6a6 9b7097e b82e6a6 1829fd6 b82e6a6 8b274aa b82e6a6 6d66777 b82e6a6 374c72e 15e8c2d b82e6a6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 |
import os
import asyncio
import logging
import tempfile
import time
import shutil
from datetime import datetime, timedelta
from moviepy.editor import VideoFileClip, AudioFileClip, CompositeAudioClip, ColorClip, TextClip, CompositeVideoClip
import edge_tts
import gradio as gr
# Configuración avanzada de logging
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
handlers=[
logging.FileHandler("video_generator.log"),
logging.StreamHandler()
]
)
logger = logging.getLogger(__name__)
# Directorio temporal personalizado con limpieza automática
TEMP_DIR = "temp_media"
os.makedirs(TEMP_DIR, exist_ok=True)
def clean_old_files():
"""Elimina archivos temporales con más de 24 horas"""
now = time.time()
cutoff = now - (24 * 3600)
for filename in os.listdir(TEMP_DIR):
file_path = os.path.join(TEMP_DIR, filename)
if os.path.isfile(file_path):
file_time = os.path.getmtime(file_path)
if file_time < cutoff:
try:
os.remove(file_path)
logger.info(f"Eliminado archivo antiguo: {filename}")
except Exception as e:
logger.error(f"Error al eliminar {filename}: {e}")
async def text_to_speech(text, voice="es-ES-ElviraNeural"):
"""Convierte texto a voz y guarda en archivo temporal"""
clean_old_files()
output_path = os.path.join(TEMP_DIR, f"tts_{datetime.now().strftime('%Y%m%d%H%M%S')}.mp3")
try:
logger.info(f"Generando TTS para texto de {len(text)} caracteres")
communicate = edge_tts.Communicate(text, voice)
await communicate.save(output_path)
return output_path
except Exception as e:
logger.error(f"Error en TTS: {e}")
raise
def create_audio_loop(audio_path, target_duration):
"""Crea un loop de audio hasta alcanzar la duración objetivo"""
try:
audio = AudioFileClip(audio_path)
if audio.duration >= target_duration:
return audio.subclip(0, target_duration)
loops_needed = int(target_duration // audio.duration) + 1
clips = [audio] * loops_needed
looped_audio = concatenate_audioclips(clips).subclip(0, target_duration)
return looped_audio
except Exception as e:
logger.error(f"Error al crear loop de audio: {e}")
raise
def create_video_with_text(text, duration, size=(1280, 720)):
"""Crea un video simple con texto centrado"""
try:
# Fondo del video
bg_clip = ColorClip(size, color=(30, 30, 30), duration=duration)
# Texto con ajuste automático de tamaño
text_clip = TextClip(
text,
fontsize=28,
color='white',
font='Arial-Bold',
size=(size[0]-100, size[1]-100),
method='caption',
align='center'
).set_position('center').set_duration(duration)
return CompositeVideoClip([bg_clip, text_clip])
except Exception as e:
logger.error(f"Error al crear video con texto: {e}")
raise
async def generate_video_content(text, background_music=None, use_tts=True):
"""Función principal que genera el contenido del video"""
try:
clean_old_files()
# 1. Procesar audio principal
if use_tts:
voice_path = await text_to_speech(text)
main_audio = AudioFileClip(voice_path)
else:
# Si no usamos TTS, creamos un audio silencioso de la duración estimada
estimated_duration = max(5, len(text.split()) / 3) # Estimación basada en palabras
main_audio = AudioFileClip(lambda t: 0, duration=estimated_duration)
duration = main_audio.duration
# 2. Procesar música de fondo
final_audio = main_audio
if background_music:
try:
bg_music_loop = create_audio_loop(background_music, duration).volumex(0.2)
final_audio = CompositeAudioClip([bg_music_loop, main_audio])
except Exception as e:
logger.error(f"Error al procesar música de fondo, continuando sin ella: {e}")
# 3. Crear video
video_clip = create_video_with_text(text, duration)
video_clip = video_clip.set_audio(final_audio)
# 4. Guardar resultado
output_path = os.path.join(TEMP_DIR, f"video_{datetime.now().strftime('%Y%m%d%H%M%S')}.mp4")
video_clip.write_videofile(
output_path,
fps=24,
threads=4,
codec='libx264',
audio_codec='aac',
preset='fast',
logger=None
)
return output_path
except Exception as e:
logger.error(f"Error en generate_video_content: {e}")
raise
finally:
# Cerrar todos los clips para liberar recursos
if 'main_audio' in locals():
main_audio.close()
if 'bg_music_loop' in locals():
bg_music_loop.close()
if 'video_clip' in locals():
video_clip.close()
# Interfaz Gradio mejorada
with gr.Blocks(title="Generador de Videos Avanzado", theme="soft") as app:
gr.Markdown("""
# 🎥 Generador de Videos Automático
Crea videos con voz sintetizada y música de fondo
""")
with gr.Tab("Configuración Principal"):
with gr.Row():
with gr.Column():
text_input = gr.Textbox(
label="Texto del Video",
placeholder="Escribe aquí el contenido de tu video...",
lines=5,
max_lines=20
)
with gr.Accordion("Opciones Avanzadas", open=False):
use_tts = gr.Checkbox(
label="Usar Texto a Voz (TTS)",
value=True
)
voice_selector = gr.Dropdown(
label="Voz TTS",
choices=["es-ES-ElviraNeural", "es-MX-DaliaNeural", "es-US-AlonsoNeural"],
value="es-ES-ElviraNeural",
visible=True
)
bg_music = gr.Audio(
label="Música de Fondo",
type="filepath",
sources=["upload"],
format="mp3"
)
generate_btn = gr.Button("Generar Video", variant="primary")
with gr.Column():
video_output = gr.Video(
label="Video Resultante",
format="mp4",
interactive=False
)
status_output = gr.Textbox(
label="Estado",
interactive=False
)
# Lógica para mostrar/ocultar selector de voz
use_tts.change(
fn=lambda x: gr.Dropdown(visible=x),
inputs=use_tts,
outputs=voice_selector
)
# Función principal de generación
def generate_video(text, use_tts, voice, bg_music):
try:
if not text.strip():
raise ValueError("Por favor ingresa un texto para el video")
# Limpieza inicial
clean_old_files()
# Generación del video
video_path = asyncio.run(
generate_video_content(
text=text,
use_tts=use_tts,
background_music=bg_music
)
)
return video_path, "✅ Video generado con éxito"
except Exception as e:
logger.error(f"Error en la generación: {str(e)}")
return None, f"❌ Error: {str(e)}"
generate_btn.click(
fn=generate_video,
inputs=[text_input, use_tts, voice_selector, bg_music],
outputs=[video_output, status_output]
)
if __name__ == "__main__":
# Limpieza inicial de archivos antiguos
clean_old_files()
# Configuración del servidor
app.launch(
server_name="0.0.0.0",
server_port=7860,
show_error=True,
share=False,
favicon_path=None
) |