This project uses Teachable Machine with sound recognition to create fun, interactive aliens that dance in real time based on audio input. The AI is trained to recognize different sounds.When the microphone captures sound, the model instantly processes it and sends commands to animate the aliens, making them move or jump, with the rhythm.
The backend is powered by JavaScript, which handles sound input, model predictions, and animation logic. On the frontend, HTML and CSS are used to design colorful, animated alien characters and a smooth user interface. This project demonstrates how sound-based AI can turn simple audio into lively visual interactions, blending creativity, and fun.
Press "Run AI" and make the aliens dance to your sound
This project uses voice recognition to control a drawing canvas and create shapes using spoken commands. The system is powered by the Web Speech API, specifically webkitSpeechRecognition, which listens to the user’s voice through the microphone and converts speech into text in real time. When the user says “Circle”, “Rectangle”, or “Triangle”, the recognized command is processed instantly.
The logic is handled with JavaScript, where the speech recognition result is matched with predefined shape commands and then drawn on the HTML5 Canvas. HTML provides the canvas structure, while CSS styles the interface for a clean, modern, and interactive look. The entire process feels natural—just speak, and the canvas responds visually.
This project demonstrates how voice-controlled interfaces can replace traditional input methods, combining speech recognition with graphics to create an intuitive and futuristic user experience.
Press “Run AI”, say a shape name, and watch it appear on the canvas
This project is a voice-based chatbot that can listen, understand, and reply to you using speech, creating a natural conversation experience. The chatbot uses speech recognition to capture your voice input through the microphone and convert it into text. That input is then processed by the chatbot’s logic to generate an appropriate response.
Once a response is created, the system uses text-to-speech (TTS) to speak back to the user, making the interaction feel human-like and engaging. The core functionality is built with JavaScript, using the Web Speech API for both voice input (speech recognition) and voice output (speech synthesis). HTML and CSS are used to design a clean chat interface that visually displays the conversation alongside the voice interaction.
This project showcases how voice-controlled AI communication works in real time and demonstrates the future of hands-free, conversational interfaces. It’s ideal for virtual assistants, smart applications, and accessibility-focused solutions.
Press “Run AI”, speak to the chatbot, and start a live voice conversation