app.py

import os

import gradio as gr
from TTS.api import TTS

os.environ["COQUI_TOS_AGREED"] = "1"
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2", gpu=False)


def process_inputs(audio, text):
    # Generate speech by cloning a voice using default settings
    tts.tts_to_file(
        text=text,
        file_path="output.wav",
        speaker_wav=audio,
        language="en",
    )
    return "output.wav"


iface = gr.Interface(
    fn=process_inputs,
    inputs=[
        gr.Audio(type="filepath", label="Sample Voice (> 6 sec)"),
        gr.Textbox(label="Text Input"),
    ],
    outputs=[
        gr.Audio(type="filepath", label="Text to Speech"),
    ],
    title="Audio and Text Processing App",
    description="Enter audio and text inputs, and get processed audio and text-to-speech outputs.",
)

iface.launch(debug=True)