speak.py

import os
import streamlit as st
import google.generativeai as genai
import speech_recognition as sr
from gtts import gTTS
import tempfile

# Configure the API with your API key
genai.configure(api_key="")

# Create the model and set up the generation configuration
generation_config = {
    "temperature": 1,
    "top_p": 0.95,
    "top_k": 40,
    "max_output_tokens": 8192,
    "response_mime_type": "text/plain",
}

# Initialize the model
model = genai.GenerativeModel(
    model_name="gemini-1.5-flash",
    generation_config=generation_config,
    system_instruction="You are an AI assistant answering questions about artificial intelligence. Respond concisely and clearly.",
)

# Start the chat session with predefined AI-related context
chat_session = model.start_chat(
    history=[
        {
            "role": "user",
            "parts": [
                "What is artificial intelligence?",
            ],
        },
        {
            "role": "model",
            "parts": [
                "Artificial intelligence (AI) refers to the simulation of human intelligence in machines designed to think and act like humans. It involves learning, reasoning, problem-solving, perception, and language understanding.",
            ],
        },
        {
            "role": "user",
            "parts": [
                "What are the types of machine learning?",
            ],
        },
        {
            "role": "model",
            "parts": [
                "Machine learning can be classified into three main types: supervised learning, unsupervised learning, and reinforcement learning. Each has its own approach and application in AI tasks.",
            ],
        },
    ]
)

# Initialize speech recognition
recognizer = sr.Recognizer()

# Set up speech-to-text function
def listen_to_audio():
    with sr.Microphone() as source:
        print("Listening for your input...")
        recognizer.adjust_for_ambient_noise(source)
        audio = recognizer.listen(source)
        
    try:
        print("Recognizing your speech...")
        user_input = recognizer.recognize_google(audio)
        print(f"You said: {user_input}")
        # user_input = generate_speech(user_input)

        # Create audio tag to play the bot's response on the webpage
        # st.audio(user_input, format="audio/mp3")
        return user_input
    except sr.UnknownValueError:
        print("Sorry, I couldn't understand your speech.")
        return ""
    except sr.RequestError:
        print("Sorry, there was an issue with the speech recognition service.")
        return ""

# Set up text-to-speech function for the bot's response
def generate_speech(text):
    tts = gTTS(text)
    # Use a temporary file to store the generated speech
    with tempfile.NamedTemporaryFile(delete=False) as tmpfile:
        tmpfile.close()
        tts.save(tmpfile.name)
        return tmpfile.name

# Streamlit UI
st.title("Voice Assistant with AI")

# Option to start listening to user's voice input
if st.button("Start Listening"):
    user_input = listen_to_audio()

    if user_input:
        # Send the user input to the chat model and get the response
        response = chat_session.send_message(user_input)
        bot_response = response.text

        # Display user input and bot response as text
        st.markdown(f"""
        <div style="display: flex; flex-direction: column; margin-bottom: 10px;">
            <!-- User's input on the right -->
            <div style="display: flex; justify-content: flex-end; margin-bottom: 10px;">
                <div style="background-color: #f1f1f1; padding: 10px; border-radius: 5px; max-width: 80%; word-wrap: break-word;">
                    <strong>You 🧑 :</strong> {user_input}
                </div>
            </div>
        #     <!-- Bot's response on the left -->
        #     <div style="display: flex; justify-content: flex-start; margin-bottom: 10px;">
        #         <div style="background-color: #e0e0e0; padding: 10px; border-radius: 5px; max-width: 80%; word-wrap: break-word;">
        #             <strong>Bot 🤖:</strong> {bot_response}
        #         </div>
        #     </div>
        # </div>
        # """, unsafe_allow_html=True)

        # Generate speech for the bot's response
        bot_audio_path = generate_speech(bot_response)

        # Create audio tag to play the bot's response on the webpage
        st.audio(bot_audio_path, format="audio/mp3")

# Display exit option
if st.button('Exit'):
    st.stop()