app.py

import gradio as gr
import nltk
import os
os.system('python -m unidic download')
from melo.api import TTS

nltk.download('averaged_perceptron_tagger_eng')

# Get device
device = 'auto'
model = TTS(language='EN', device=device)
speaker_ids = model.hps.data.spk2id


def inference(text: str):
    output_path = 'en-us.wav'
    model.tts_to_file(text, speaker_ids['EN-US'], output_path, speed=1.0)
    return output_path


if __name__ == "__main__":
    demo = gr.Interface(
        fn=inference,
        inputs=[
            gr.Textbox(),
        ],
        outputs=[
            gr.Audio()
        ],
    )
    demo.queue().launch()