OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Vocalinux

Vocalinux is an AGPL-3.0-licensed Linux desktop application that transcribes speech and types the result into whichever application has focus. Its local recognition engines include whisper.cpp, Whisper, Faster Whisper, VOSK and Parakeet; an optional remote HTTP API is separate from its on-device workflow.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Vocalinux — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Vocalinux when you want microphone-based dictation across Linux desktop applications and can meet its Python, display-session and microphone requirements.

Who it is for

  • Linux users who want to dictate text directly into desktop applications.
  • People seeking local speech recognition after downloading a model.
  • Users who want to choose among several recognition engines or use push-to-talk and toggle dictation.

Documented uses

  • Dictate text into the currently focused application.
  • Insert punctuation and line breaks with voice commands.
  • Use voice commands to delete the last sentence or capitalize the next word.
  • Choose a recognition engine and model for a local dictation workflow.
Before you choose

Requirements & limits

  • Python 3.11 or newer is required; the distribution must provide the distro PyGObject dependency.
  • A microphone is required, while a Vulkan-capable GPU is optional.
  • The default engine is whisper.cpp; other documented engine choices include OpenAI Whisper, Faster Whisper, VOSK and Parakeet.
  • The optional remote HTTP API is not on-device recognition and is off unless configured.
  • Text injection uses desktop tools such as xdotool, IBus, wtype or ydotool, with clipboard fallback.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Use push-to-talk dictation

Dictate text into the application that currently has focus.

Before you start

  • Linux with Python 3.11 or newer
  • An X11 or Wayland session
  • A microphone
  • Install Vocalinux and download a speech model

Steps

  1. Launch Vocalinux from the application menu or run its vocalinux command.

  2. With the default push-to-talk mode on a new installation, hold Right Alt and speak into the microphone.

  3. Release the key to stop dictation and inject the recognized text into the focused application.

Expected outcome

Recognized speech is entered as text in the focused application.

Guide limitations

  • An existing configuration may retain a previously saved shortcut.
  • Local speech recognition requires a downloaded model.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
VocaHQ/vocalinux · Official homepage title · retained in its source language
How we review sourcesSuggest a correction