🤝 Top Collaborators
.png&w=640&q=75)
.png&w=640&q=75)
🤓 Latest Submissions
ClearVoice 2.0
Over 70 million individuals worldwide live with speech dysfluencies such as stuttering, blocks, repetitions, and mid-sentence restarts. In our voice-first digital world, conventional AI systems fail them: traditional Voice Activity Detection (VAD) abruptly terminates recording during brief pauses, speech-to-text creates garbled repetition bloat, and unconstrained language models introduce dangerous factual hallucinations like altering numbers or stripping negations. ClearVoice 2.0 solves this by introducing a real-time, sub-second speech repair and neural resynthesis pipeline. Built with a high-performance polyglot architecture, our Python core engine uses PyTorch Silero VAD with a custom 1,500ms adaptive silence window and 512-sample frame slicing to eliminate premature cutoffs, streaming live audio directly to AssemblyAI's Realtime WebSocket API. When speech is transcribed, our Node.js intelligence server leverages Groq-hosted open-weights models alongside a 6-utterance rolling context buffer to intelligently remove dysfluencies while preserving intentional emphasis. To guarantee zero hallucination, a deterministic Meaning Validator rigorously inspects every repair, ensuring critical numbers, dates, negations, and named entities remain 100% faithful to the original speech. If any drift is detected, an automated zero-trust fallback engine serves a conservatively cleaned or raw transcript. Approved speech is resynthesized through a resilient 3-tier failover engine: primary high-fidelity streaming via ElevenLabs PCM16, secondary on-server system TTS via pyttsx3, and tertiary browser-level client synthesis. Deployed in a Dockerized AWS EC2 backend with an interactive Next.js 16 frontend on Vercel, ClearVoice 2.0 democratizes voice interfaces and empowers dysfluent speakers with clarity, dignity, and confidence.
30 Sep 2026
Autonomous Multi Agent AI trading system
This project is a fully autonomous, multi-agent AI trading system built on top of the Alpaca Trading API. Our architecture leverages a sophisticated pipeline of specialized AI agents working in tandem to identify, analyze, and execute profitable options and equity trades. The pipeline begins with a Deterministic Filter that scans live market data to identify high-probability setups based on volume, liquidity, and implied volatility. These candidates are then passed to our Market Agent (for technical thesis generation) and News Agent (for real-time sentiment analysis). An Options Agent synthesizes this data to construct optimal multi-leg strategies. Finally, a Risk Assessment Engine mathematically validates every trade against strict portfolio constraints—such as max daily loss and exposure limits—before our Execution Agent routes the orders live to Alpaca. To visualize this complex orchestration, we built a stunning, real-time Next.js dashboard. It provides traders with an interactive command center to monitor live portfolio equity, track individual AI agent decisions, view strategy payoff charts, and audit the complete execution lifecycle. By combining strict quantitative risk management with advanced LLM reasoning, we’ve created an institutional-grade trading terminal.
4 Sep 2026
