web-audio-api

yogsgehlot/Chatbot-Song-Recommender-System

Tooling and datasets for neural-network powered audio feature based synthesis

🎧 A full-stack Shazam-like music recognition app that identifies songs from short audio clips using FFT-based fingerprinting and real-time matching. (Kindly find the fronted part attached below)

Real-time AI assistant powered by Gemini 2.5 Flash Native Audio — sees your camera, speaks back. Built with FastAPI + React.

The digital monolith behind my own website: Django 6 ASGI, real-time Web Audio DSP, and strict CSP runtime.

Personal project. A privacy-first, on-device noise monitor that timestamps barking events and sound-level spikes and turns them into a clean report.

AI voice receptionist for clinics: books, reschedules and cancels real appointments via LLM tool calls, in English and 中文. Eval-driven debugging: 53% → 87% across 30 scripted caller scenarios.

ΔΟΚΙΜΑΣΙΑ — o escrutínio, e o que ele revela. ΠΟΛΙΟΡΚΗΤΙΚΟΣ · ΛΟΓΟΣ · ΒΑΣΙΛΕΙΑ · ΦΑΝΗΣ. Vitrine de um experimento epistêmico multiagente; código em breve. / The scrutiny and what it reveals — showcase of a multi-agent epistemic experiment.

Agentic African Audio Signal Processing & MLOps Engine for polyrhythms, DSP feature extraction, and self-correcting threshold optimization.

KIMIX is a clonable hybrid audio platform that runs as both a standalone Python application and a Web Audio browser-based listening environment. Clean. Accurate. No fluff.

Turn any phone, tablet, or laptop into a wireless speaker for your PC via local WebSockets and Web Audio API. Lightweight and zero-install client.

ear the space around you — binaural sonification of ultrasonic echoes · ACTAM 2025/26

Synth Nest — browser-based synthesizer and generative sound design environment

Acoustic Keyed Cipher, WAV PCM LSB Steganographer, Morse Synthesizer, and Studio (design influenced by Material 3)

🎛️ Real-time 3D Eurorack Synthesizer hero experience & interactive audio lab built with Three.js, GSAP, Web Audio API, and Blender Draco 3D assets.

Real-time speech orchestration and audio stream visualizer with live rolling word buffers, bidirectional IPC integration with Adrastea, and low-latency TTS voice playback.

Analyze any video in your browser and get a science-based age recommendation for children — 100% local, nothing is uploaded.

🎸 High-performance AI Grunge Jam Generator (v2.0.0). FastAPI, Google Magenta (Melody RNN), FluidSynth & Zero-Disk Streaming with real-time Web Audio oscilloscope.

Machines tell you before they break. Unsupervised acoustic predictive maintenance running entirely in a browser tab.