import gradio as gr
from huggingface_hub import InferenceClient
import torch
from TTS.api import TTS
import soundfile as sf

# Load TTS Model (supports multiple models)
tts_model = TTS("tts_models/en/ljspeech/tacotron2-DDC").to("cuda" if torch.cuda.is_available() else "cpu")

# Hugging Face LLM client
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content
        response += token
        yield response, None  # Yielding text response first

    # Generate speech from text response
    output_audio_path = "response.wav"
    tts_model.tts_to_file(text=response, file_path=output_audio_path)
    
    yield response, output_audio_path  # Yielding audio response

# Gradio Chat Interface with Audio Output
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
    outputs=[
        gr.Textbox(label="Generated Response"),
        gr.Audio(type="filepath", label="TTS Output"),
    ],
)

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