app.py

import gradio as gr
from transformers import pipeline
import scipy.io.wavfile

# Initialize the text-to-speech pipeline
synthesiser = pipeline("text-to-speech", "suno/bark-small")

def text_to_speech(text):
    # Generate speech
    speech = synthesiser(text, forward_params={"do_sample": True})
    
    # Save to a WAV file
    output_file = "bark_out.wav"
    scipy.io.wavfile.write(output_file, rate=speech["sampling_rate"], data=speech["audio"])
    
    return output_file

# Create Gradio interface
demo = gr.Interface(
    fn=text_to_speech,
    inputs=gr.Textbox(label="Enter Text", placeholder="Type something..."),
    outputs=gr.Audio(label="Generated Speech", autoplay=True)
)

# Launch the app
#if __name__ == "__main__":
demo.launch()