Leonid Kostash
Offer Leonid work on your next project.
Private message
Offer work
Rovno,
Ukraine
23 days 19 hours back
a little busy
age 45 years
on the service 11 years
Rating
Successful projects
Average rating
Skills and abilities
Programming
Design & art
Photo, Audio & Video
Translation
Portfolio
-
Telegram bot for teachers: example in biology
AI & Machine Learning
Telegram bot for teachers that:
- conducts interactive quizzes;
- explains material to students in chat;
… - voices answers in Ukrainian;
- recognizes text from photos and documents;
remembers conversation history for personalized explanations.
This is a universal tool for fast and modern learning that can be adapted for any subject.
The bot is equipped with a built-in quiz generator that allows teachers to quickly create questions for interactive learning. Using a simple and user-friendly graphical interface on Tkinter, a teacher can:
*Add questions with different answer options.
*Specify the correct answer option.
*Choose the difficulty level of the question and its category (e.g., "Zoology," "Genetics").
*Edit or delete existing questions.
*Clear all questions for a new quiz.
All questions are stored in a JSON file, making it easy to save, edit, and share materials.
Key features of the quiz generator:
Quick creation and customization of quizzes without the need to write code.
Easy access to all data through a convenient interface.
Automatic saving of all changes to the file.
-
Voice AI assistant on the website: simple prototype
AI & Machine Learning
The idea to create a voice #AI assistant that understands language and responds meaningfully came quite simply. Many services offer chatbots, but they are often limited to text or formal communication. I wanted to make it so that a user could just speak to their computer or phone and receive real, useful answers — without extra clicks and long waiting times.
How it works:
For voice recognition, I used the standard Web Speech API, which is supported by modern browsers. This allows you to simply press a button and speak, and the browser recognizes the text and sends it for processing.
Responses are generated using large language models (LLMs), which operate through an API — this enables receiving high-quality and relevant answers without complex local infrastructure.
…
The responses are voiced through the ResponsiveVoice library, which currently provides the most natural voices for the web interface. Although there was an initial attempt — to add support for local voices, such as RHVoice, but they sounded less natural.
-
79 USD SmartBot AI
AI & Machine Learning
AI panel based on a local Flask server with built-in functions:
telegram-bot
cryptobot OKX
image and text analysis and recognition with LLM models
… AI prompts for cryptocurrency analysis
-
SmartBot OKX (DEMO)
Cryptocurrency & Blockchain
Features
Connection to OKX API (sandbox only)
Interface in Ukrainian and Russian
Set TP / SL per position
… CoinGecko live chart
Position table with profit/loss highlights
ROE calculation with leverage
Smart Assistant: strategy hints
EXE protected (Themida)
