In today’s world, our fast-paced lives rarely allow us the luxury of remembering every detail from important meetings—or those long Dungeons & Dragons sessions. As a multi-tasker with a notoriously poor memory when it comes to meetings and collaborative gaming sessions, I set out to build a system that not only captures audio on a per-process basis but also transforms it into structured, actionable insights. This post outlines our progress in building a native Windows audio capture engine using Rust and wasapi‑rs, and how it feeds into a real-time streaming pipeline for transcription, summarization, and even diarization.
Read more →