GitHub

A set of C++ classes that provide a common API for realtime audio input/output across Linux (native ALSA, JACK, PulseAudio and OSS), Macintosh OS X (CoreAudio and JACK), and ...

RtAudio is a set of C++ classes that provides a common API (Application Programming Interface) for realtime audio input/output across Linux (native ALSA, JACK, PulseAudio and OSS), Macintosh OS X and ...
note

I added my own voice to the away-from-desk summary tool, and the audio part broke

Last time, I wrote about a locally running "away-from-desk summary" tool. It transcribes the audio from a study session and summarizes only the parts where I was away from my seat. At the end of the ...
GitHub

Real-Time Offline Speech Translator (Windows)

Fully offline. No cloud APIs. Uses a timing gate: when TTS plays translated audio, the loopback capture is suppressed for the playback duration + 200ms buffer. This prevents the system from ...
note

I'm doomed if I step away during a study session where Japanese, Chinese, and English fly around. I built an 'away-from-keyboard summary' tool using local AI

It's low-key terrifying to step away from your desk during online study sessions or seminars. When I attend technical study sessions online, Japanese, English, and Chinese are often mixed together ...