Show HN: Sys2txt – transcribe system audio to text in the CLI with a local LLM

A developer released sys2txt, a command line tool that records audio playing on a Linux machine through PulseAudio/PipeWire's monitor source and transcribes it live with OpenAI's Whisper speech-to-text model. The tool supports faster-whisper, openai-whisper, and whisper.cpp with Vulkan GPU support for AMD hardware, and can either record-then-transcribe once or stream continuously in segments with live output in txt, srt, vtt, json, and tsv formats. The developer, who said they have been using and developing the tool since November 2025, is seeking collaborators to extend it to other operating systems and hardware.

sys2txt is a command line tool that records whatever audio your Linux machine is playing via PulseAudio/PipeWire's monitor source and transcribes it live with Whisper, OpenAI's AI-based speech-to-text model. I use it to caption meetings, videos, and calls playing on my own machine without routing audio through anything else. It supports faster-whisper, openai-whisper, and whisper.cpp with Vulkan GPU support for AMD , and can either record-then-transcribe once or stream continuously in segments with live output in txt/srt/vtt/json/tsv. I'd be keen to collaborate with others extend its functionality to other operating systems and hardware. I have been using and developing this tool since November 2025. Comments URL: https://news.ycombinator.com/item?id=50129017 https://news.ycombinator.com/item?id=50129017 Points: 2 Comments: 0