app.py

import spaces
import gradio as gr
from TTS.api import TTS
import os

os.environ["COQUI_TOS_AGREED"] = "1"

device = "cpu"

tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to(device)

@spaces.GPU(enable_queue=True)
def clone(text, audio):
    tts.tts_to_file(text=text, speaker_wav=audio, language="en", file_path="./output.wav")
    return "./output.wav"

iface = gr.Interface(
    fn=clone,
    inputs=[gr.Textbox(label='Text'), gr.Audio(type='filepath', label='Voice reference audio file')],
    outputs=gr.Audio(type='filepath'),
    title='Voice Clone',
    description="by Tony Assi — CPU-only version",
)
iface.launch()