Rocky f197b68573 feat(keyboard): add clipboard voice command mode
Long-press mic runs ASR as an instruction over eligible clipboard text,
with host-confirm recording UI, min-record gate, and light ASR prewarm.
Bump CURRENT_PROJECT_VERSION to 53.
2026-08-07 16:08:42 +08:00
2026-06-17 23:08:58 +08:00

OSGKeyboard

Speak it. It's typed.

Voice input for iPhone, iPad, and Mac. Speak in any app — polished text lands at your cursor.

Platform Platform Swift Version License

Website · 中文 README · Privacy Policy

Download now from the App Store   Download now — macOS version


Why OSGKeyboard

  • Works everywhere — Messages, Notes, Notion, Cursor, Mail, WeChat — wherever you type
  • Speak, don't edit — tap (iOS) or hold Option (Mac); AI adds punctuation and structure for you
  • Type in Chinese and English — iOS keyboard ships full/double pinyin candidates, plus English autocomplete, autocorrect, and next-word prediction
  • On-device by default — local recognition on iOS; optional local models on Mac. Cloud upload only when you opt in
  • Bring your own LLM — built-in polish out of the box, or plug in DeepSeek, OpenAI, Anthropic, OpenRouter, and more
  • Mac global dictation — menu-bar app, bottom overlay with live feedback, inserts into the frontmost app

Three steps

  1. Install & authorize — add the iOS keyboard with Full Access; grant mic + Accessibility on Mac
  2. Pick an engine — local ASR + built-in polish (zero config), or your own API keys
  3. Start talking — switch to OSGKeyboard, or hold Option on Mac

Platforms

iOS / iPadOS macOS
Keyboard / global hotkey hold Option
Chinese typing (full / Microsoft / Sogou double pinyin) optional fuzzy pairs
English typing (autocomplete / autocorrect / next-word) offline lexicon + personal-dictionary boosts
Local speech recognition SpeechAnalyzer SenseVoice / Qwen3
AI polish
Post-polish translation
Personal dictionary iCloud sync; protects polish and boosts English suggestions
Dictation history
Live UI — (silent background keep-alive) floating pill

Privacy

Speech is transcribed on-device by default. Polish sends text only — the transcript and a small amount of nearby cursor text for continuity, never raw audio. Chinese candidate learning and English suggestion/autocorrect learning stay in the on-device App Group and are not uploaded. Secure fields disable English suggestions and autocorrect. Cursor context is not logged or saved to voice history. See the Privacy Policy.


Get the app

iPhone / iPad (App Store)

Download now from the App Store

Mac (Developer ID signed and notarized)

Download now — macOS version

Build from source

Requires macOS with Xcode 26 and XcodeGen.

git clone https://github.com/hkgood/OSGKeyboard.git
cd OSGKeyboard
./Scripts/generate-xcodeproj.sh
open OSGKeyboard.xcodeproj

Run tests:

xcodebuild test -project OSGKeyboard.xcodeproj -scheme OSGKeyboard \
  -destination 'platform=iOS Simulator,name=iPhone 17'

Architecture (brief)

OSGKeyboard/          Main iOS app (Flow session host)
OSGKeyboardExt/       Custom keyboard extension
OSGKeyboardMac/       macOS menu-bar app
OSGKeyboardShared/    Shared framework (ASR, LLM, sync, design system)

Flow session model (iOS): the host app keeps a long-lived audio session; the keyboard sends start/stop signals via App Group; polished text is delivered back for insertion.

Engine modes:

  • local — on-device ASR; built-in polish (or your own LLM key)
  • cloud — uploads audio to your configured ASR provider, then polishes via LLM

See CHANGELOG.md for release history and CONTRIBUTING.md for PR guidelines.


Adding an LLM provider

Append a preset in OSGKeyboardShared/Models/LLMProvider.swift — any OpenAI-compatible /chat/completions endpoint works out of the box.


Acknowledgements

OSGKeyboard's voice and keyboard features build on these projects and platforms:

See Third-Party Notices for exact versions and licenses (Chinese Rime stack plus the OSG-owned English lexicon notice), or open Settings → About → Third-Party Licenses in the app.


License

Source Available License — personal, non-commercial use only. Commercial licensing: rocky.hk@gmail.com.

S
Description
No description provided
Readme 57 MiB
Languages
Swift 93.7%
Python 4.6%
Shell 0.8%
HTML 0.5%
Objective-C++ 0.3%