realtime-audio

Live multi-effect guitar pedalboard in C++17 for the pi-Stomp (Raspberry Pi 5): 30+ JUCE-DSP effects, Neural Amp Modeler, lock-free RCU chain editing, LVGL on-device UI + Svelte/SSE web control

Phone-callable voice agent: Vobiz XML <Stream> bridged to the Gemini Live API. No audio resampled anywhere, real barge-in, and a mock client that holds a whole conversation without placing a call.

WebSocket Speechmatics Flow bridge for AVR: receives PCM audio from avr-core and streams STS audio responses in real time.

macOS app that measures and trains musical timing from MIDI. Swift, 926 tests, one self-checking quality gate. Built with Claude Code under my direction and verification.

Enterprise Realtime Voice AI Technical Interviewer — Adaptive System Design & Resume Deep-Dive with Deepgram Nova-2, OpenAI & ElevenLabs.

Realtime RVC voice changer for AMD Ryzen AI (XDNA 2 NPU) - ONNX Runtime, VitisAI EP, DirectML, CPU; C++20 + ImGui, Python model conversion tools

Low-latency osu! hitsounds for Linux. Per-key samples fired the instant you press, for osu!, mania, and other rhythm games.

An Autonomous AI Tutor Web App leveraging the Socratic Method for education. Powered by Gemini Live Audio, Next.js, FastAPI, RAG, and local GLM-OCR.

Eight-Voice Dual-Sample Stereo Sampler for ESP32-S3

An iOS voice-first capture assistant: talk to it, and it turns what you said into structured tasks, ideas, and notes you can find again. SwiftUI, realtime audio, on-device semantic search.

LAN voice intercom with Opus codec, jitter buffer, and optional native C++ mixer

First-party transport connectors for sending PocketStation AudioBuses to external systems.

Phoenix Librarian is the companion Windows application for the **RTAL Project Phoenix** hardware sampler. It was developed to make the complete Phoenix bank structure accessible from a PC without turning the sampler into a computer-dependent instrument.

Play music together over the internet, in real time. Up to six people, encrypted and straight between your computers — no server in the middle, no account to create.

Tumburu Digital Audio Workstation

Realtime sequencer core in the Elektron p-lock tradition, plus panelspec: behaviour specs that verify any implementation

Provider-neutral voice turn-taking decisions and causal evaluation for real-time agents

Playable remix and vocal chop instrument in Rust. Slice a sample, map the chops across the keyboard, and play the same slice differently on every key. VST3, CLAP and standalone.

real-time audio calls via webRTC with text translations - Klusterthon hackathon 2023

FastAPI backend for real-time phone-call translation and AI agent mode using Amazon Nova 2 Sonic and Twilio