
Most language apps teach you to read and recognize a language — not to speak it. Flashcards and grammar drills never touch the actual skill: producing sentences out loud, in real time, under mild social pressure. Human tutors help, but they're expensive and scheduled. Practicing alone gives you silence instead of feedback. Maya fixes that by being a real-time, voice-first conversation partner. Open the browser and start talking — voice activity detection knows when you start and stop, so it feels like an actual phone call. Maya transcribes what you say, replies out loud with an LLM, and the moment you finish speaking, a feedback panel shows three things: What you said (your raw transcript, filler words and all), What you meant (a cleaned-up version of your intended sentence), and More natural (how a native speaker would actually phrase it, with the key change highlighted). You can also select any word mid-conversation for an instant dictionary lookup — definition, part of speech, US/UK pronunciation audio, and example sentences with Chinese translations — and save anything into a personal library to review later. Under the hood: a FastAPI backend, faster-whisper/whisperx for speech-to-text, Fireworks AI or a local Ollama model for reasoning, and Edge TTS or a local CSM-1B model for speech synthesis. Every stage in the loop has a fully local, self-hostable option, so the whole conversation can run offline on-device without a per-token cloud bill. Cached filler audio ("Sure.", "Got it.") plays instantly in Maya's own voice to mask model latency while the real reply generates. Currently supports English and Chinese practice. Built on top of teammate KaushikSiva's original real-voice repo for the 2026 AMD Hackathon.
12 Jul 2026

YOLO Street is an AI-powered autonomus trading agent that helps everyday investors discover, compare, and understand stock opportunities and then buy. It analyzes market news, company fundamentals, price trends, and user risk preferences to generate simple explanations, watchlists, and portfolio suggestions. Instead of overwhelming users with charts and jargon, YOLO Street AI like a co-pilot for investing: it explains why a stock may be interesting, what risks to watch, and how it fits into a small portfolio. For a Robinhood-style experience, the app could let users ask questions like “What should I buy with $200?” or “How does Nvidia’s photonics investment affect AI stocks?” and receive clear, beginner-friendly investment ideas.
31 May 2026

Time Circle is a reflective productivity experience designed for people who struggle with distraction, burnout, or fragmented focus. Instead of aggressively blocking apps or punishing users for losing focus, Time Circle approaches attention with softness, ritual, and visual feedback. When a user opens a restricted app such as YouTube, Chrome, or social media, the system gently prompts them with a minimal floating interface. The user chooses a state like Working, Learning, or Break, then draws an open circle with their mouse. The unfinished circle becomes a small floating fragment on the desktop, quietly reminding them that their attention is still “open.” When the restricted app is closed, the app automatically restores the fragment and softly completes the circle animation. The system records the start time, end time, state, goal, and app usage into structured logs. AI-generated reflections then appear in a calm completion screen, transforming raw screen time into emotionally meaningful feedback. Rather than treating distraction as failure, Time Circle visualizes the idea that meaningful work is built through returning many times. The project combines behavioral psychology, ambient interaction design, lightweight AI reflection systems, and handcrafted visual aesthetics inspired by journals and slow living. Over time, the accumulated behavioral logs are analyzed by AI to identify emotional patterns, focus cycles, and attention drift habits. Instead of generating productivity scores or punishment systems, the AI acts more like a reflective companion — offering gentle observations, personalized reflections, and emotionally aware feedback based on how the user actually spends their time. The project was built as an experimental productivity ritual exploring how AI can support healthier relationships with attention, focus, and digital habits.
19 May 2026