VocaHQ/vocalinux

Free, open-source, 100% offline voice dictation for Linux. Speak and type anywhere via whisper.cpp, Whisper & VOSK engines, GPU-accelerated, works on X11 + Wayland!

What it solves

Vocalinux provides a privacy-focused, on-device voice dictation tool for Linux users. It allows users to convert speech to typed text in any active application without relying on cloud services, solving the problem of lacking native, high-quality speech-to-text (STT) integration across different Linux distributions and display servers (X11 and Wayland).

How it works

The application runs local speech-to-text engines on the user's machine. After an initial model download, all audio processing happens locally. It supports multiple engines, including whisper.cpp (the default), OpenAI Whisper, Faster Whisper, VOSK, and Parakeet. To inject text into other apps, it uses tools like xdotool, IBus, wtype, or ydotool.

Who it’s for

Linux users who want a seamless voice dictation experience with high privacy, as no account is required and audio stays on-device. It is designed to work across major distributions like Ubuntu, Debian, Fedora, and Arch Linux.

Highlights

  • On-device processing: Audio is processed locally after model download for maximum privacy.
  • Multi-engine support: Supports whisper.cpp, OpenAI Whisper, Faster Whisper, VOSK, and Parakeet.
  • GPU acceleration: Utilizes Vulkan for AMD, Intel, and NVIDIA GPUs via whisper.cpp.
  • X11 and Wayland compatibility: Works across both major Linux display servers.
  • Voice commands: Includes built-in support for punctuation and basic formatting commands (e.g., "new line", "period").
  • Flexible installation: Available via install script, .deb, .rpm, AppImage, AUR, Flatpak, and Snap.

Related

  • Project
    goodroot/hyprwhspr

    hyprwhspr is a native Linux speech‑to‑text app that runs as a system‑wide service. It uses local models (Whisper, Cohere, Parakeet, Qwen3‑ASR, etc.) for near‑real‑time dictation, optionally falls back to cloud APIs, and integrates with Wayland/X11 desktops, status bars, and a themed visualiser. Install via the AUR or a one‑line script, configure with `hyprwhspr setup`, then toggle dictation with `Super+Alt+D` to have transcribed text auto‑pasted into any window.

  • Project
    akshayaggarwal99/jarvis-ai-assistant

    An open-source voice dictation tool that converts speech to text anywhere on your system, supporting local transcription and LLM post-processing for privacy and speed.

  • Project
    peteonrails/voxtype

    Voxtype is an open‑source, MIT‑licensed Linux app that provides local, real‑time voice‑to‑text dictation. It runs fast CPU models (Cohere Transcribe 9‑11× realtime) and supports GPU/Intel NPU acceleration, nine interchangeable transcription engines, multilingual support, meeting‑mode transcription, and deep desktop integration (Wayland/X11, hotkey binding, auto‑pause media, waveform OSD). All processing stays on the machine unless the user opts for a remote server.

  • Project
    TypeWhisper/typewhisper-mac

    A system-wide speech-to-text and AI text processing utility for macOS that supports local and cloud transcription engines with customizable AI workflows.

  • Project
    karansinghgit/speaktype

    A free, open-source voice-to-text tool that allows you to dictate text into any application locally on your computer for maximum privacy.