Antonio R.

A browser extension acting as a private, true Live Interpreter. It captures tab audio via a local WhisperLive server or reads existing video subtitles, translating and playing them aloud (TTS) in real-time. Optimized for low-resource PCs to run independently of cloud services whenever possible. Compatible with Windows, macOS, and Linux.

playlist4whisper manages media streams playlists for livestream_video.sh, plays media, and transcribes audio via AI with configurable timeshift, multi-instance/user support, translation, and TTS. Compatible with Linux, Windows (WSL2), macOS.

Complete GPU passthrough setup for KVM/QEMU on Linux, enabling near-native Windows VM performance with dedicated GPU access. Covers NVIDIA and AMD GPUs with comprehensive troubleshooting.

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

[CVPR 2026] tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction

An advanced AI-powered Bluetooth phone switchboard using Gemini Live and Whisper.cpp. It acts as a real-time smart secretary, handling incoming calls, filtering SPAM, taking messages, and logging transcripts.