{"full_name":"anomalyco/hex","owner":"anomalyco","name":"hex","shard":"1","url":"https://github.com/anomalyco/hex","description":"Local voice dictation for mac, windows and linux","homepage":"https://anoma.ly/hex","topics":["dictation","linux","local-first","macos","rust","speech-recognition","speech-to-text","voice-control"],"tag_pages":["linux","local-first","macos","rust","speech-recognition","speech-to-text"],"language":"Rust","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/66570915?v=4","created_at":"2026-07-17T23:48:56Z","pushed_at":"2026-11-17T21:32:29Z","metrics":{"stars":7279,"forks":472,"watchers":12,"issues":734,"prs":1210,"releases":25,"issues_open":183,"issues_closed":551,"prs_open":43,"prs_closed":85,"prs_merged":1082,"discussions":0},"growth":{},"history":{"dates":["2026-11-18"],"stars":[7279],"forks":[472],"watchers":[12],"issues_open":[183],"prs_open":[43]},"boards":{},"same_owner":[{"full_name":"anomalyco/opencode","name":"opencode","shard":"1","boards":{"daily":80,"weekly":106,"monthly":32,"daily_rate":188,"daily_forks":101,"total":25}},{"full_name":"anomalyco/opentui","name":"opentui","shard":"1","boards":{}},{"full_name":"anomalyco/rune","name":"rune","shard":"1","boards":{"weekly":192,"weekly_rate":103,"monthly_rate":118,"new":86}},{"full_name":"anomalyco/sst","name":"sst","shard":"1","boards":{}}],"issues":[{"number":988,"title":"Windows: stuck on “Enabling…” — microphone initialization fails with E_INVALIDARG (0x80070057)","comments":19,"created_at":"2026-11-02T12:23:46Z"},{"number":650,"title":"Keep spoken Commands behind a Labs flag","comments":13,"created_at":"2026-10-31T19:11:38Z"},{"number":603,"title":"Transcription through an OpenAI-compatible endpoint","comments":11,"created_at":"2026-10-31T16:56:00Z"},{"number":287,"title":"On screen text display, memory, multiple machine memory and edit options.","comments":11,"created_at":"2026-10-28T14:52:04Z"},{"number":859,"title":"Feature request: Named speakers in meeting transcripts","comments":10,"created_at":"2026-11-01T17:23:42Z"},{"number":802,"title":"Make Hex settings easy to share between devices","comments":10,"created_at":"2026-11-01T11:40:57Z"},{"number":729,"title":"iPhone: option to transcribe on a Mac running Hex","comments":10,"created_at":"2026-11-01T01:41:42Z"},{"number":1370,"title":"Linux: make the paste keystroke configurable","comments":8,"created_at":"2026-11-05T09:21:15Z"}],"discussions":[],"latest_release":{"name":"Hex 3.4.0","tag":"v3.4.0","published_at":"2026-11-11T04:30:30Z","body":"## Hex 3.4.0\n\n> **windows, coming from 3.3:** if hex shows \"download update\" instead of updating itself, download setup ([x64](https://anoma.ly/hex/download/windows-x64-setup) · [arm64](https://anoma.ly/hex/download/windows-arm64-setup)) and run it over your existing copy. don't uninstall first: settings, history and models stay, and later updates install themselves again.\n>\n> **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 globalshortcuts`. binds that run `hex dictation …` need no change.\n\n### new\n\n- the first run is one story now: a bad group chat, the same conversation with hex, then your own first words\n- the interface speaks russian (русский)\n- new speech models: orukeet, granite speech 5.0 470m turboctc, and nb-whisper medium for norwegian. models that hear the language themselves sit under auto\n- history's header is one \"kept 7 days ▾\" menu: retention, keep audio too, and clear all history…\n- each history entry names the model and language that heard it, and replace keeps up to five earlier versions (transcribing an entry again needs its audio, kept with keep audio too)\n- meetings (opt-in): names and summaries are one choice, off, on this mac or opencode (off or opencode on windows and linux), so a transcript never goes to opencode unless you pick it\n- meeting rows show the call app's icon, and discord calls are detected like slack and teams\n- toggle mode has its own cancel shortcut, escape by default, and there is no pre-roll when \"while dictating\" mutes, pauses or lowers other audio\n- transcribe again asks which language to use for that run on models that take a language, and the vocabulary sheet says how many terms the selected model reads\n- scroll bars are always visible and draggable on linux and windows, and menus take page up/down and home/end\n- touchscreens: taps, drags and momentum scrolling work in hex's windows\n- the window, hud and capsules have names, values and states for screen readers and voice control\n- windows: hex.exe no longer opens a console from the start menu or login, and hex.com runs it in a terminal. logs and models move to local appdata once\n- windows: `POST /dictations` uses hex's own microphone and can stream live text\n- mac: the menu bar is ordered meeting, actions, then app, with the speech model and shortcuts in it\n- mac: your shortcuts keep working while another app holds secure input, like a password field or a terminal's secure keyboard entry\n\n### labs (off by default)\n\n- screenshots on mac: ⌘⇧4 draws a crosshair over any app, a thumbnail slides in, and the editor has pen, arrow, box, text, crop, copy, save and send to. recordings save at native resolution in hevc and wait in the corner until you close them\n- mac: a notch indicator for the hud, caps lock to dictate hands-free, annotate's last 15 seconds (macos 27 and later, with annotate on and screen recording allowed), and audio files imported as meetings\n- up to four more dictation shortcuts on mac, each with its own activation mode, and a second one on linux and windows that uses the main shortcut's activation mode\n- a speech model and language per mode that follow the app in front on mac and windows, and \"while dictating\" that only applies on speakers\n- play kept history recordings, write meeting notes to their own file, live typing through the wayland input method, and transform typed text in the focused field on linux\n\n### fixes\n\n- mac: a microphone that goes silent or dies mid-dictation is reopened instead of losing the dictation, and an interrupted dictation is kept and copied instead of thrown away\n- mac: the hud rejoins every space, works in the bottom position and with the notch, the live text plate no longer flashes the last d","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-17T21:58:29Z","history_start":"2026-09-06"}