Caption meetings and calls on Linux with local Whisper
sys2txt records whatever audio your Linux machine is playing and transcribes it live with Whisper, faster-whisper or whisper.cpp, with output in txt, srt, vtt, json or tsv.
Source
joeheffer on Hacker News · 2026-10-17 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-23.
What they did
sys2txt records whatever audio your Linux machine is playing and transcribes it live with Whisper, faster-whisper or whisper.cpp, with output in txt, srt, vtt, json or tsv.
Result (as claimed)
Meetings and calls get captioned without routing audio through another service.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Map the task
Write the trigger, the inputs, the decisions and the output. Note which steps need a human yes.
Connect the tools
Set up sys2txt, Whisper with the narrowest permissions that work. Use a test account or sandbox first.
Build the workflow
Create the steps in order. Add an approval step before anything sends, pays or deletes.
Run it on real but low-stakes data
Run a few times, read every output, and fix prompts or rules that misfire.
Schedule and monitor
Turn on the schedule or trigger, and add a daily summary or alert so you notice failures.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Caption meetings and calls on Linux with local Whisper What the original author did: sys2txt records whatever audio your Linux machine is playing and transcribes it live with Whisper, faster-whisper or whisper.cpp, with output in txt, srt, vtt, json or tsv. Reported result (as claimed by the author): Meetings and calls get captioned without routing audio through another service. Source: https://news.ycombinator.com/item?id=50129017 Tools they used: sys2txt, Whisper Category: Automation & business Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Caption meetings and calls on Linux with local Whisper What the original author did: sys2txt records whatever audio your Linux machine is playing and transcribes it live with Whisper, faster-whisper or whisper.cpp, with output in txt, srt, vtt, json or tsv. Reported result (as claimed by the author): Meetings and calls get captioned without routing audio through another service. Source: https://news.ycombinator.com/item?id=50129017 Tools they used: sys2txt, Whisper Category: Automation & business Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Caption meetings and calls on Linux with local Whisper What the original author did: sys2txt records whatever audio your Linux machine is playing and transcribes it live with Whisper, faster-whisper or whisper.cpp, with output in txt, srt, vtt, json or tsv. Reported result (as claimed by the author): Meetings and calls get captioned without routing audio through another service. Source: https://news.ycombinator.com/item?id=50129017 Tools they used: sys2txt, Whisper Category: Automation & business Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to take meeting notes and track follow-ups with AI · How to use AI agents for Linux, servers and homelabs
Related use cases
Transcribe interviews and meetings offline with a local AI studio
TrueScribe, built with help from AI coding agents, turns interviews, meetings, lectures and podcasts into text on your own machine, with review, translation, search and export on Windows and Linux.
Get a 7 AM brief of calls, emails and overdue invoices with drafts held for approval
He rebuilt Claude Duet's main features in Grok Bot in about 10 minutes, using this prompt: "Every day at 7:00 send me a morning brief: today's calls, emails that need my answer, overdue invoices, and the one thing to do first. Draft replies, but send nothing without my approval." He also set up inbox sorting, calendar moves around a focus block and invoice reminders.
Self-host an AI teammate with local models and approval before risky steps
He built LocalCrew, a self-hosted assistant inspired by Grok Bot that runs on local models, keeps persistent tasks, uses browser tools and asks for human approval before sensitive actions.
Control your coding agent with a walkie-talkie
walkai-talkai lets you talk to Cursor, Claude Code or Antigravity hands-free through a walkie-talkie and hear the agent's answers back over the radio, with local Whisper speech-to-text so audio stays on your Mac.