#86 · Primary category: Speech & Audio
voxtype
Voice-to-text with push-to-talk for Wayland compositors
Project last updated:08/29/26
GitHub Stars
1.3K
Forks
100
Contributors
34
License
MIT
Why we included this project
For anyone who dictates a lot on a Linux desktop, voxtype is a fully local push-to-talk tool. Hold a hotkey while you speak and the text appears at your cursor when you release; the default Cohere Transcribe engine runs 9-11x faster than realtime on a mid-range CPU, with six other engines for different hardware and languages. On Wayland it hooks into Hyprland, Sway, GNOME, KDE, and Niri keybindings, falls back through wtype, dotool, or the clipboard if a layer is unavailable, and pauses your music over MPRIS while you dictate. There's also a meeting mode with continuous transcription, speaker attribution, and Markdown or SRT export for use beyond solo dictation.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
whisper.cpp
Port of OpenAI's Whisper model in C/C++
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
VibeVoice
Open-Source Frontier Voice AI
voicebox
The open-source AI voice studio. Clone, dictate, create.
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production