app.py

import gradio as gr
import os
import spacy
import torch
from transformers import pipeline
import speech_recognition as sr
from gtts import gTTS
import tempfile
import base64

# Install required Spacy model
os.system("python -m spacy download en_core_web_sm")
nlp = spacy.load("en_core_web_sm")

# Load Hugging Face model (Example: Bloom or other LLM from Hugging Face)
chat_model = pipeline("text-generation", model="bigscience/bloom-560m")

# Speech-to-Text function
def transcribe_audio(audio_path):
    recognizer = sr.Recognizer()
    with sr.AudioFile(audio_path) as source:
        audio_data = recognizer.record(source)
        try:
            return recognizer.recognize_google(audio_data)
        except sr.UnknownValueError:
            return "Could not understand the audio."

# AI Chat Response
def chat_with_ai(user_input):
    response = chat_model(user_input, max_length=150, do_sample=True, temperature=0.7)
    return response[0]['generated_text']

# Text-to-Speech function
def generate_speech(text):
    tts = gTTS(text=text, lang='en')
    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
    tts.save(temp_file.name)
    with open(temp_file.name, "rb") as audio_file:
        encoded_audio = base64.b64encode(audio_file.read()).decode("utf-8")
    os.unlink(temp_file.name)
    return encoded_audio

# Chat Interface
def chat_interface(user_input, audio_file=None):
    if audio_file is not None:
        user_input = transcribe_audio(audio_file)
    
    ai_response = chat_with_ai(user_input)
    audio_response = generate_speech(ai_response)
    
    return ai_response, f"data:audio/mp3;base64,{audio_response}"

# Create Gradio UI
gui = gr.Interface(
    fn=chat_interface,
    inputs=[
        gr.Textbox(lines=2, placeholder="Type your message here..."),
        gr.Audio(source="upload", type="filepath", optional=True)
    ],
    outputs=[
        gr.Textbox(label="AI Response"),
        gr.Audio(label="AI Voice Response")
    ],
    title="AI Chat Assistant",
    description="An AI-powered chat assistant with text & voice input/output.",
    theme="huggingface"
)

gui.launch()