themanyone/voice_typing
State-of-the-art offline (or networked) voice typing everywhere + text terminals (Linux or WFL session on Windows.) with a simple bash script. Usable with X. Does not require X.
Implements a modular client-server architecture where `voice_typing` runs Whisper locally (loading/unloading per utterance for minimal memory), while `voice_client` optionally connects to a persistent `whisper-server` instance for faster continuous dictation—supporting GPU acceleration via CUDA and quantized models down to 48 MiB VRAM. Text injection uses `ydotool` virtual keyboard daemon, enabling hands-free input across any window manager or headless environment, with voice activity detection via `sox` and optional Silero VAD for improved accuracy in noisy conditions.
154 stars.
Stars
154
Forks
9
Language
Shell
License
GPL-2.0
Category
Last pushed
Mar 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/themanyone/voice_typing"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jatinkrmalik/vocalinux
Free, open-source, 100% offline voice dictation for Linux. Speak and type anywhere via...
mkiol/dsnote
Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to...
peteonrails/voxtype
Voice-to-text with push-to-talk for Wayland compositors
oddlama/whisper-overlay
A wayland overlay providing speech-to-text functionality for any application via a global...
gurjar1/OmniDictate
Free, open-source, real-time dictation for Windows. Runs locally (no cloud!), uses AI, and types...