OSGKeyboard
Speak naturally.
Get polished text anywhere.
A source-available keyboard that transcribes your voice on-device, then polishes — and optionally translates — the result. Works in every app you type in.
Notes
Tomorrow at 3 PM, sync with the design team on the new onboarding flow.|
Everything you need to type by voice
On-device by default, refined by AI when you want it — in a single, native keyboard.
Tap-to-talk dictation
Tap to start, tap to stop. Up to 3.5 minutes per take, with a live countdown.
On-device recognition
iOS 26 SpeechAnalyzer transcribes on your device by default — audio is uploaded only if you explicitly enable the cloud engine.
AI polish
Punctuation, structure, and clarity in three intensity levels. Polish sends only text — on the default engine your audio never goes online.
Built-in translation
Translate after polish into English, 中文, 日本語, 한국어 and more — right from the keyboard.
Personal dictionary
Keep names, products, and jargon accurate. The AI preserves your terms every time.
Flow session
A long-lived session keeps the recorder warm, so you can dictate take after take.
Three steps to your first message
Set up once, then dictate anywhere you type.
Enable the keyboard
Add OSGKeyboard in iOS Settings and allow Full Access — needed for the mic and network.
Choose your engine
Local: on-device ASR with built-in polish, no API key. Cloud: use your own OpenAI-compatible key.
Tap to talk
Switch to OSGKeyboard, tap the mic, speak, tap again. Polished text lands at your cursor.
Your voice stays yours
Speech is processed on-device by default (the optional cloud engine uploads recordings to the provider you configure). We never log ordinary keystrokes; polish and translation receive only transcribed text.