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 seamless, privacy-focused voice-to-text experience for Linux users. It allows users to dictate text into any application regardless of whether they are using X11 or Wayland, filling a gap in native Linux voice typing capabilities.

How it works

The app runs as a desktop application that captures audio and converts it to text using one of three on-device speech recognition engines: whisper.cpp (the default), OpenAI Whisper, or VOSK. It uses Vulkan for universal GPU acceleration across AMD, Intel, and NVIDIA hardware. Once a model is downloaded, all processing happens locally on the user's machine. The resulting text is then injected into the active application via IBus or other injection methods.

Who it’s for

Linux desktop users who want a high-quality, private, and system-wide voice dictation tool that works across different distributions (such as Ubuntu, Debian, Fedora, and Arch).

Highlights

  • On-device processing: Speech-to-text remains local after the initial model download for maximum privacy.
  • Flexible Engine Choice: Supports whisper.cpp for high performance, OpenAI Whisper for PyTorch users, and VOSK for low-RAM systems.
  • Universal Linux Support: Compatible with X11 and Wayland across major distributions.
  • Customizable Activation: Offers both toggle and push-to-talk modes with configurable keyboard shortcuts.
  • GPU Acceleration: Utilizes Vulkan for broad hardware compatibility.
  • Neural VAD: Includes Silero Voice Activity Detection to improve recording accuracy.

Related

  • Project
    goodroot/hyprwhspr

    A native Linux speech-to-text tool that provides fast, private, and system-wide dictation using local or cloud-based AI models.

  • Project
    OpenWhispr/openwhispr

    OpenWhispr is a cross‑platform desktop app that converts speech to text, provides live meeting transcription with speaker diarisation, and lets you talk to AI assistants (GPT‑5, Claude, Gemini, etc.) directly from your keyboard. It works offline with Whisper‑based models or via cloud services, stores notes locally (with optional cloud sync), and offers an API for programmatic use.

  • Project
    peteonrails/voxtype

    A local voice-to-text tool for Linux that transcribes speech to text at the cursor position using various AI engines without cloud dependency.

  • Project
    collabora/WhisperLive

    WhisperLive is an open‑source, near‑real‑time transcription server built around OpenAI’s Whisper model. It supports multiple inference back‑ends (faster‑whisper, NVIDIA TensorRT, Intel OpenVINO, AMD ROCm), offers word‑level timestamps, hot‑word boosting, speaker diarization and optional translation, and provides both simple command‑line clients and a Python streaming API. Docker images are provided for GPU and CPU deployments, and browser/iOS extensions let you transcribe audio directly from a web page or mobile device.

  • Project
    altic-dev/FluidVoice

    An open-source voice-to-text dictation app for macOS that enables on-device AI transcription and system control via voice commands.