Open source · iOS 26+

Hold to talk.
Polished text in any app.

A custom keyboard that transcribes your voice on-device and optionally polishes the result with the LLM you configure — WeChat, Notes, Mail, ChatGPT, and everywhere else you type.

On-device ASR Bring your own API Zero dependencies
9:41●●●

Notes

OSGKeyboard active

Tomorrow at 3 PM, sync with the design team on the new onboarding flow. Send the draft before lunch.

Built for real typing workflows

Native SwiftUI, privacy-first architecture, and a Typeless-style push-to-talk experience.

Push-to-talk

Press and hold the mic key, speak naturally, release — polished text lands at your cursor.

On-device ASR

Speech stays on your iPhone. Apple's on-device speech stack handles transcription — audio never leaves the device.

AI polish

Optional cloud pass adds punctuation, structure, and clarity. Only the transcript is sent — not your voice.

Bring your own API

Works with any OpenAI-compatible endpoint: OpenAI, DeepSeek, Qwen DashScope, or your own server.

Privacy first

No ordinary keystroke logging. You choose when cloud polish runs and which provider receives text.

Lean & native

Pure Swift 6 and SwiftUI — no CocoaPods, no Carthage, no third-party packages.

How it works

Three gestures between thought and sent message.

Enable the keyboard

Install from source, turn on OSGKeyboard in iOS Settings, and allow Full Access for mic + your API.

Hold the mic

Switch to OSGKeyboard in any text field, press and hold the circular record button, and speak.

Release to insert

On-device transcription runs instantly; optional LLM polish returns clean text right where you type.

Privacy at a glance

Audio is processed on your device. We do not log ordinary keystrokes. In cloud polish mode, only transcribed text — never audio — goes to the API provider you configure.

Read full policy