app.py

import gradio as gr
from TTS.api import TTS

tts = TTS(
    model_name="tts_models/multilingual/multi-dataset/xtts_v2",
    gpu=False
)

def synthesize(text, speaker_wav):
    out = "out.wav"
    tts.tts_to_file(
        text=text,
        speaker_wav=speaker_wav,
        language="en",
        file_path=out
    )
    return out

ui = gr.Interface(
    fn=synthesize,
    inputs=[
        gr.Textbox(label="Text"),
        gr.Audio(type="filepath", label="Speaker voice (wav)")
    ],
    outputs=gr.Audio(type="filepath"),
    title="XTTS Voice Cloning (CPU)"
)

ui.launch()