vocalinux and MySuperWhisper
These are competitors—both provide offline voice-to-text dictation for Linux using Whisper as the speech recognition engine, with largely identical functionality (Wayland/X11 support, local processing), so users would select one based on maturity and feature preferences rather than use them together.
About vocalinux
jatinkrmalik/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!
Vocalinux is a free, offline voice dictation application for Linux users, helping you type by speaking into any application on your desktop. It takes your spoken words as input and outputs them as text, allowing you to control documents, emails, or forms with your voice. This tool is ideal for anyone on Linux who wants to improve their productivity or accessibility by using voice commands instead of typing.
About MySuperWhisper
OlivierMary/MySuperWhisper
A global voice dictation tool for Linux using local OpenAI Whisper. Fast, accurate, and works on Wayland/X11.
Implements global hotkey detection with configurable multi-tap triggers (single/double/triple press) and voice command post-processing that intelligently adapts output formatting for terminal emulators versus standard applications. Integrates with PulseAudio/PipeWire for audio capture, supports CUDA INT8 quantization for GPU acceleration, and provides multilingual voice commands (French, English, Spanish) alongside a system tray interface for device selection and model switching.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work