anomalyco /hex

Local voice dictation for mac, windows and linux

★ 7,279⑂ 472👁 12⑃ 1,210● 734▤ 25
RustMITCreated 2026-07-17anoma.ly/hex
下载:Hex 3.4.0Hex-3.4.0 ↓3.4.02026-11-11
7,279
stars
472
forks
12
watchers
1,210
prs
734
issues
25
releases

README

Hex

Hex is local voice dictation for Mac, Windows and Linux. Hold a key, speak, and
it pastes.

 How it works

- hold the shortcut, speak, then let go
- Hex transcribes on your device and pastes into whatever app you're in
- the first run downloads a speech model; after that nothing leaves your machine
- experimental features live in Labs, at the bottom of the sidebar

 What it does

- hold the shortcut to dictate, or set Shortcut mode to Tap to start and stop
  with a press
- the text lands at the cursor in whatever app you're in
- Option-Shift-V pastes the last dictation again (Ctrl-Alt-V on Windows and Linux)
- History keeps your dictations, searchable, for 7 days by default
- Output runs every dictation through steps you choose (word replacements,
  built-in cleanups, your own scripts, an optional OpenCode rewrite), with
  different steps per app or website
- Vocabulary is one list of names Hex should know; Whisper and Qwen3-ASR read
  it while transcribing, Parakeet models read it with Labs › Vocabulary help
  on, and the OpenCode rewrite uses it
- Annotate records the screen while you draw and talk, on macOS, Linux and
  Windows (GNOME Wayland needs Labs › Annotate on GNOME)
- an authenticated local API and the TypeScript SDK
  transcribe with the same model, for your own tools
- Meetings is a macOS lab that records a call and writes the transcript

Output and History:





 Speech models

Hex downloads one model the first time it runs and transcribes with it on your
machine from then on. On an English system that's Parakeet Unified English: it
writes while you talk, so the text is ready when you let go. Other languages
start with the model recommended for them. That model also serves meetings and
hex transcribe.

Settings' picker offers more, among others:

- Parakeet v3: 25 European languages, and it hears which one you speak
- Cohere Transcribe: the fewest wrong words, in 14 languages; a big download
- Whisper large-v3-turbo: almost any language, and it reads your vocabulary
- Qwen3-ASR 0.6B: Chinese and 29 more, and it reads your vocabulary
- SenseVoice Small: Chinese, Japanese, Korean and English; a small download
- Nemotron 3.5 ASR: writes while you talk, in 27 languages
- Granite Speech 5.0: IBM's model, seven languages, with punctuation
- one-language models: ivrit.ai Whisper for Hebrew, GigaAM v3 for Russian,
  NB-Whisper for Norwegian, QwenCleo-ASR for Egyptian Arabic
- more English models: Parakeet v2 and Underdog Bark 3.0

Add a GGUF model of your own with "Add model file…" in the picker; see
your own speech models.

 Downloads

Stable is the current release. Dev is the newest build of dev and updates
itself from the dev channel.

| Platform | Stable | Dev |
| --- | --- | --- |
| macOS (Apple silicon) | DMG | DMG |
| Windows x64 | Installer | Installer |
| Windows ARM64 | Installer | Installer |
| Linux x86_64 | Executable | Executable |
| Linux x86_64 (Debian, Ubuntu) | .deb | .deb |
| Linux x86_64 (Fedora, openSUSE) | .rpm | 

Top issues

Latest release

Hex 3.4.0 v3.4.0 2026-11-11
Hex 3.4.0

 windows, coming from 3.3: if hex shows "download update" instead of updating itself, download setup (x64 · arm64) and run it over your existing copy. don't uninstall first: settings, history and models stay, and later updates install themselves again.

 hyprland, coming from 3.3: binds to the old names with the key in them (anomaly.hex:dictation-ALT-space) still work for the key you had, but switch them to the fixed names before you record another key: anomaly.hex:dictation, anomaly.hex:paste-last, anomaly.hex:capture, anomaly.hex:raw-dictation. reload your config and check hyprctl

Snapshot: 2026-11-17T21:58:29Z · Data license Apache-2.0 · JSON