Update app.py

app.py

@@ -24,15 +24,8 @@ def generate_audio(text, language, speaker_wav):
     if speaker_wav is not None:
         audio = tts.tts(text=text, speaker_wav=speaker_wav, language=language)
     audio_np = np.array(audio, dtype=np.float16)
-    # Codificar como WAV en memoria
-    import soundfile as sf
-    buffer = BytesIO()
-    sf.write(buffer, audio_np, 24000, format="WAV")
-    buffer.seek(0)
-
-    # Codificar a base64
-    audio_b64 = base64.b64encode(buffer.read()).decode("utf-8")
-    return f"data:audio/wav;base64,{audio_b64}"
+    return (24000, audio_np)
+    
 
 # 🎛️ Interfaz
 iface = gr.Interface(
@@ -42,7 +35,7 @@ iface = gr.Interface(
         gr.Text(label="Idioma (ej: 'es', 'en')"),
         gr.Audio(type="filepath", label="Audio de voz")
     ],
-    outputs=gr.Textbox(label="Audio generado")
+    outputs="audio"
 )
 
 iface.launch()