Back to Projects

Voco

Started Page updated
A voice-native layer for Linux
Voco's canonical silver microphone mark with the Linux emblem

A small desktop utility for Linux: press Alt+D, speak naturally, and review the locally recognized text pasted into your focused field.

Current release2026.0.59 · Ubuntu/Debian
Default routeLocal and offline
Reference desktopUbuntu · Wayland/X11

Latest verified release

2026.0.59 is the published Ubuntu/Debian release, released 2026-09-23 and checked 2026-10-03. Fedora, openSUSE and Arch/Omarchy packages remain at 2026.0.43.

This update fixes GNOME shortcut reservation and Stop handling, includes the Brave text-preservation fixes from 2026.0.58, and corrects installer cleanup. The recognition model is unchanged. Follow the upgrade guidance to load GNOME companion version 4.

Release notes and downloads

Why Voco exists

A new machine revealed a missing gesture.

I switched to Linux a few weeks ago after becoming disappointed with Apple and its MacBook Pro. These used to be the creme de la creme when it came to high end laptops. I do not believe that still holds true anymore. These machines are very heavy, no longer as aesthetically impressive as they once were, and still are very expensive. I decided to try out a Lenovo ThinkPad because of my keen interest in experimenting with Linux. I love it, and with the current advancements in agents operating in CLIs, I now have a machine that is very powerful at a third of the price with assistants helping learn how to use it and build things for it.

The desktop had intelligence. It lacked a native voice gesture.

With this new change come new challenges. Not all the applications I was used to, or potential new ones, are immediately available. That can also be seen as a great opportunity to learn and build.

The idea

What if speaking felt native?

This is where Voco, my latest mini project, enters the conversation. I loved seeing how people are now dictating to their CLIs instead of typing, not just to CLIs, but in fact to a lot of applications. I really liked the idea and wanted to give it a try. To my surprise, Whisper Flow is not yet available on Linux. But what if I could build it myself? That could save me a few pounds at the expense of some precious tokens.

  1. Voicemicrophone
  2. Audio sampleslocal capture
  3. Local transcriptNemotron · CPU
  4. Focused fieldclipboard paste
Alt+D

Under the surface

Default dictation stays inside the laptop.

Voco is a free, open source desktop dictation tool for Linux. Press Alt+D to start speaking and again to stop. The current release runs a local English NVIDIA Nemotron model on the CPU, with no GPU, account or cloud transcription required. It pastes the transcript into the focused text field and never presses Enter. For privacy, audio stays on your device; update checks contact GitHub.

Normal Alt+D stays local
  1. CaptureNative microphone capture on Wayland; browser capture on X11
  2. Native engineLocal English NVIDIA Nemotron model · CPU
  3. Desktop deliveryClipboard paste · review before sending

The cursor contract

Speak naturally. Review before sending.

Text arrives through clipboard paste, replacing the clipboard contents. Keep the target field focused until dictation stops, then review before sending. Interrupted transcripts remain available in Voco for recovery.

Local recognition speech to text

your voice becomes text here

Text delivery clipboard paste
Delivery interruptedrecover the transcript in Voco

Sessions are limited to ten minutes. Voco never presses Enter, and generic desktop paste cannot safely rewrite an entire message after Stop.

Your voice stays local. You decide when to send.

Voco 2026.0.59 · Ubuntu/Debian · amd64 .deb