app.py

import gradio as gr
from TTS.api import TTS

# Initialize Coqui TTS with XTTS-v2
tts = TTS(model_name="coqui/XTTS-v2", progress_bar=False)

def generate_speech(text):
    output_file = "/tmp/output.wav"
    tts.tts_to_file(
        text=text,
        file_path=output_file,
        speaker_wav="reference.wav",  # Replace with the path to your reference audio
        language="en"                # Specify the language (e.g., "en" for English)
    )
    return output_file

# Create a Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("# Coqui XTTS-v2 Demo")
    gr.Markdown("Type some text and hear it spoken!")
    
    input_text = gr.Textbox(label="Enter Text", placeholder="Type something...")
    output_audio = gr.Audio(label="Generated Speech", type="filepath")
    
    submit_button = gr.Button("Generate Speech")
    submit_button.click(generate_speech, inputs=input_text, outputs=output_audio)

demo.launch(share=True)