Skip to main content
This guide walks you through building a simple multilingual FAQ chatbot using the Spitch API.

​
🔧 Prerequisites

Before you start, make sure you have:
  • Python 3.10+
  • Spitch Python SDK
  • A Spitch API key

​
🚀 Installation

Install the required packages: 
pip install spitch

​
Code Walkthrough

​
1. Import and Setup

We import the necessary modules, set the API key, and initialize the Spitch client. 
import os
from spitch import Spitch

# Set up Spitch client
os.environ["SPITCH_API_KEY"] = "your_api_key_here"
client = Spitch()

​
2. FAQ Database

We define a simple English-based FAQ dictionary. 
faq_db = {
    "hi": "hello. how may I help you",
    "what are your opening hours": "Our support team is available 24/7 to assist you.",
    "how can i reset my password": "To reset your password, click on 'Forgot Password' on the login page.",
    # ... more FAQs here
}

​
3. Translation Function

This helper function uses Spitch’s text translation service. 
def translate(text, source_lang, target_lang):
    translation = client.text.translate(
        text=text,
        source=source_lang,
        target=target_lang,
    )
    return translation.text.lower()

​
4. FAQ Matching

Matches the normalized user input against the FAQ database. 
def get_response(user_input):
    normalized = user_input.strip().lower()
    for question, answer in faq_db.items():
        if question in normalized:
            return answer
    return "I'm sorry, I didn't understand that. Could you please rephrase?"

​
5. Main Chat Loop

This is where the chatbot runs interactively. 
def main():
    print("Welcome to Multilingual Support Chatbot!")
    source_lang = input("Enter your language code (e.g., 'yo' for Yoruba, 'ig' for Igbo): ")

    while True:
        user_input = input("You: ")
        if user_input.lower() in ["exit", "quit"]:
            print("Goodbye!")
            break

        # Translate to English for matching
        input_en = translate(user_input, source_lang, "en")

        # Get English response
        response_en = get_response(input_en)

        # Translate back to user's language
        response_user_lang = translate(response_en, "en", source_lang)
        print(f"Bot: {response_user_lang}")

if __name__ == "__main__":
    main()

​
🧑‍💻 Access the code here

$ git clone https://github.com/Nalito/spitch-multilingual-chatbot-python.git
$ cd spitch-multilingual-chatbot-python

​
Running the Chatbot

Run this command in your terminal: 
python chatbot.py
Enter your preferred language code, ask a question, and the bot will respond in your chosen language.

​
Example Interaction

Welcome to Multilingual Support Chatbot!
Enter your language code (e.g., 'yo' for Yoruba, 'ig' for Igbo): yo
You: Bawo ni mo se le tun oro igbaniwo mi se
Bot: lati tun oro igbaniwo re se, tẹ lori 'gbagbe oro igbaniwo' lori oju-iwe wiwọle ati tẹle awọn ilana naa.

​
Next Steps

  • Expand the faq_db with more multilingual entries.
  • Integrate with a web UI or messaging platform.
  • Add speech-to-text and text-to-speech for full voice-based interaction.