{"id":49559321,"url":"https://github.com/larryxiao/openquack","last_synced_at":"2026-05-17T23:01:13.054Z","repository":{"id":354791710,"uuid":"1224861741","full_name":"larryxiao/openquack","owner":"larryxiao","description":"Elegant voice dictation app for macOS.","archived":false,"fork":false,"pushed_at":"2026-05-03T05:43:32.000Z","size":2641,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-03T07:22:23.952Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://github.com/larryxiao/openquack","language":"Swift","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/larryxiao.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":"docs/ROADMAP.md","authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-04-29T17:50:03.000Z","updated_at":"2026-05-03T06:14:32.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/larryxiao/openquack","commit_stats":null,"previous_names":["larryxiao/openquack"],"tags_count":10,"template":false,"template_full_name":null,"purl":"pkg:github/larryxiao/openquack","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/larryxiao%2Fopenquack","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/larryxiao%2Fopenquack/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/larryxiao%2Fopenquack/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/larryxiao%2Fopenquack/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/larryxiao","download_url":"https://codeload.github.com/larryxiao/openquack/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/larryxiao%2Fopenquack/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32599415,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-03T22:12:39.696Z","status":"online","status_checked_at":"2026-05-04T02:00:06.625Z","response_time":58,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-05-03T07:11:51.746Z","updated_at":"2026-05-17T23:01:13.036Z","avatar_url":"https://github.com/larryxiao.png","language":"Swift","funding_links":[],"categories":["Audio","音声テキスト変換","Desktop \u0026 Mobile Applications","Menu Bar Apps"],"sub_categories":["オーディオ録音・処理","Snippet \u0026 Utility Tools","What It Does"],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/images/banner.png\" alt=\"OpenQuack — Speak. Send. Privately. Recording overlay shows 'Listening' with a live level meter; menu-bar popover shows 'Pasted at cursor' with the last transcript and a Settings / Quit footer.\"\u003e\n\u003c/p\u003e\n\n\u003cdiv align=\"center\"\u003e\n\n**OpenQuack** *Speak. Send. Privately.*\n\nVoice dictation for macOS. Nothing leaves your device — audio, text, nothing.\n\n[![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n[![Platform](https://img.shields.io/badge/platform-macOS%2013%2B-lightgrey.svg)](docs/INSTALL.md)\n[![Status](https://img.shields.io/badge/status-alpha-yellow.svg)](docs/ROADMAP.md)\n\n\u003c/div\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eEnglish\u003c/strong\u003e ·\n  \u003ca href=\"README.zh-CN.md\"\u003e简体中文\u003c/a\u003e ·\n  \u003ca href=\"README.ja.md\"\u003e日本語\u003c/a\u003e ·\n  \u003ca href=\"README.ko.md\"\u003e한국어\u003c/a\u003e ·\n  \u003ca href=\"README.fr.md\"\u003eFrançais\u003c/a\u003e ·\n  \u003ca href=\"README.es.md\"\u003eEspañol\u003c/a\u003e ·\n  \u003ca href=\"README.de.md\"\u003eDeutsch\u003c/a\u003e\n\u003c/p\u003e\n\n\u003e 🌐 Translations are machine-translated stubs. Native-speaker contributions very welcome — open a PR or see [`CONTRIBUTING.md`](CONTRIBUTING.md).\n\n---\n\n\u003e 📢 **What's new — [v2.0.0-alpha.12](https://github.com/larryxiao/openquack/releases/tag/v2.0.0-alpha.12):** Settings polish round — push-to-talk dropped (toggle only), FAQ rows fully clickable, History menu's \"Re-paste\" simplified to \"Copy\", and the Chinese-script picker only shows when you've set the transcription language to Chinese. Hope you like it! ([past releases](https://github.com/larryxiao/openquack/releases))\n\n## What it is\n\nOpenQuack is a tiny menu-bar app for macOS. Press a hotkey, speak, press it again — your transcript appears at the cursor. Wherever you can type, you can talk.\n\nSpeech recognition happens on your Mac. No cloud, no account, no signup, no telemetry.\n\n## Why\n\n**Local.** Everything runs on your device — recording, transcription, optional polish. Nothing leaves: no audio, no text, no telemetry, no signup. Confidential work stays confidential, by construction. And because there's no API call in the loop, it just keeps working — offline, on a plane, behind a corporate firewall.\n\n**Fast, especially on long clips.** Whisper streams while you speak, so a 5-minute dictation finishes in about 3 seconds after you stop — the wait doesn't grow with length. ~2.6% word-error rate on real human speech on a baseline M4 / 16 GB, ~6.3% in realistic office noise. Full bench matrix in [`docs/BENCHMARKS.md`](docs/BENCHMARKS.md).\n\n**Quiet on resources.** ~120 MB of RAM while idle. ~8 MB app bundle. The Whisper model lives on disk and only loads when you press the hotkey.\n\n**Open.** MIT-licensed. Every line is auditable; every change happens in public. The version running in your menu bar is the version in this repo.\n\n## What you get\n\n- **One-key dictation.** Pick a hotkey (default ⌃⇧Space, or bind `fn` / Globe). Press once to start, press again to stop.\n- **Auto-paste at the cursor** in any app. Falls back to your clipboard if you'd rather paste yourself.\n- **99 languages.** English, Chinese, Japanese, Korean, Spanish, French, German, Italian, and Portuguese are right in Settings; auto-detect on by default.\n- **Smart formatting** — capitalisation, end-punctuation, \"um/uh\" cleanup.\n- **Custom dictionary** — teach it the proper nouns and project names you actually use.\n- **Auto-stop after silence.** Finish speaking, OpenQuack wraps up on its own.\n- **Launch at login** — show up in the menu bar after every restart with one toggle.\n\n## Privacy, in one screen\n\n1. **Nothing leaves your device — audio, text, nothing.** Recording and transcription are fully local. Always.\n2. **No analytics, no telemetry, no signup.**\n\nThe full privacy contract is in [`docs/VISION.md`](docs/VISION.md#privacy-contract).\n\n## Coming next\n\n- **In-context transcription** — OpenQuack reads the surrounding text before transcribing, so domain terms get disambiguated by what you're actually doing.\n- **Thinking mode** — an opt-in second pass through a small local LLM (Ollama or MLX-LM, your pick) that turns a raw spoken sentence into one you'd press send on.\n\nBoth deferred while the adoption foundations land. See [`docs/ROADMAP.md`](docs/ROADMAP.md) for what's queued; [`docs/VISION.md`](docs/VISION.md) for where this is going overall.\n\n## Install\n\n```sh\nbrew tap larryxiao/openquack https://github.com/larryxiao/openquack\nbrew install --cask openquack\n```\n\nOr [download the DMG](https://github.com/larryxiao/openquack/releases) and drag into Applications. First launch: right-click → **Open** → **Open** (one-time Gatekeeper bypass).\n\nGrant **Microphone** when macOS asks, pick a hotkey in **Settings → Shortcut** (default ⌃⇧Space).\n\nWant a guided walkthrough? See [`docs/TUTORIAL.md`](docs/TUTORIAL.md) — five minutes from install to first dictation.\n\n### Or tell your AI agent\n\nPaste this into Claude Code, Codex, opencode, Hermes, or similar:\n\n```text\nInstall OpenQuack on this Mac:\n\n  brew tap larryxiao/openquack https://github.com/larryxiao/openquack\n  brew install --cask openquack\n\n(Or grab the DMG from https://github.com/larryxiao/openquack/releases\nand drag it into /Applications; first open right-click → Open → Open.)\n\nThen launch /Applications/OpenQuack.app, grant Microphone, and pick a\nhotkey in Settings → Shortcut. Default ⌃⇧Space.\n```\n\nMore options (uninstall, build-from-source, what's downloaded on first run): [`docs/INSTALL.md`](docs/INSTALL.md).\n\n## Got stuck? Want a feature?\n\nDrop a comment in **[Discussions](https://github.com/larryxiao/openquack/discussions/43)** — it's the lowest-friction way to reach me. Bugs, feature ideas, \"I'm using it for X\" workflow stories, or quick questions about Whisper / model choice / paste behavior in a specific app all welcome. Issues are fine for structured reports too, but no need to format.\n\nCommon questions (install, accuracy, languages, offline behaviour, Mac requirements) live in the [**FAQ on the docs site**](https://larryxiao.github.io/openquack/#faq).\n\n## Acknowledgements\n\nOpenQuack stands on the shoulders of generous open-source work. Huge thanks to:\n\n- [**OpenAI Whisper**](https://github.com/openai/whisper) — the speech model that makes any of this possible.\n- [**WhisperKit**](https://github.com/argmaxinc/WhisperKit) by Argmax — Whisper, fast and native on Apple Silicon.\n- [**KeyboardShortcuts**](https://github.com/sindresorhus/KeyboardShortcuts) by Sindre Sorhus — the hotkey machinery you press every day.\n- [**voxt**](https://github.com/hehehai/voxt) — a kindred project we learned a lot from on the technical side.\n- [**Typeless**](https://www.typeless.com/) and [**Wispr Flow**](https://wisprflow.ai/) — the closed-source apps that proved how delightful voice-first input can feel; we're aiming for the same feel, locally and openly.\n\nAnd to everyone filing issues, opening PRs, and telling friends: thank you. The duck quacks because of you.\n\n## Contribute\n\nOpenQuack is **AI-native open source** — every PR cites a SPEC, atomic tasks come from the roadmap, the workflow is friendly to coding agents at scale (and humans on the same path).\n\nStart with [`AGENTS.md`](AGENTS.md), pick a 🔵 task in [`docs/ROADMAP.md`](docs/ROADMAP.md), open a draft PR.\n\nUnder the hood: [`TUTORIAL`](docs/TUTORIAL.md) · [`DEVELOPMENT`](docs/DEVELOPMENT.md) · [`ARCHITECTURE`](docs/ARCHITECTURE.md) · [`BENCHMARKS`](docs/BENCHMARKS.md) · [`DESIGN`](docs/DESIGN.md) · [`INSTALL`](docs/INSTALL.md) · [`BLOG`](docs/blog/README.md).\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flarryxiao%2Fopenquack","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flarryxiao%2Fopenquack","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flarryxiao%2Fopenquack/lists"}