from huggingface_hub import InferenceClient
import gradio as gr
import os

client = InferenceClient(api_key=os.getenv("HF_TOKEN"))

def generate_speech(text):
    if not text.strip():
        return None
    
    try:
        audio_bytes = client.text_to_speech(
            text,
            extra_body={
                "exaggeration": 0.25,
                "temperature": 0.7,
                "audio_url": "https://huggingface.co/spaces/abidlabs/hfstudio/resolve/main/frontend/static/voices/andrew.mp3",
            }
        )
        return audio_bytes
    except Exception as e:
        raise gr.Error(f"Error generating speech: {str(e)}")

# Create the Gradio interface
with gr.Blocks(title="Text to Speech") as demo:
    gr.Markdown("# Text to Speech")
    gr.Markdown("Convert text to speech using the Chatterbox model.")
    
    with gr.Row():
        with gr.Column():
            text_input = gr.Textbox(
                label="Text to convert to speech",
                placeholder="In a hole in the ground, there lived a hobbit. Not a nasty, dirty, wet hole, filled with the ends of...",
                lines=5,
                value="In a hole in the ground, there lived a hobbit. Not a nasty, dirty, wet hole, filled with the ends of worms and an oozy smell, nor yet a dry, bare, sandy hole with nothing in it to sit down on or to eat: it was a hobbit-hole, and that means comfort."
            )
            generate_btn = gr.Button("Generate Speech", variant="primary")
        
        with gr.Column():
            audio_output = gr.Audio(label="Generated Speech")
    
    generate_btn.click(
        fn=generate_speech,
        inputs=[text_input],
        outputs=[audio_output]
    )

if __name__ == "__main__":
    demo.launch()