Dictate 5.2.0 takes dictation beyond Dictate's own keyboard: it can now act as your phone's system-wide voice input, run a freeform spoken command from anywhere, and clean up long dictations on its own. Updating shows a new What's-new tour for 5.2 — and every tour stays re-viewable under Settings › About.
🎙️ Dictate from anywhere
- System-wide voice input — Dictate now registers through all three of Android's voice-input mechanisms (a voice input IME, a
RecognitionService, and the classic speech popup), so the mic key in other keyboards and apps can transcribe through Dictate — with your provider, your prompts and your on-device models. Enable "Dictate voice input" in your keyboard list and pick it as your voice input method. Because it's a real input method, it also works in apps that block the accessibility-based floating button. (Note: Gboard hardwires its mic to Google and won't use a third-party voice input.) (#67, #237) - Freeform voice command on the floating button — long-press the button, tap Live prompt, and just say what you want: "write a polite decline for tomorrow's meeting", "translate the text above to Spanish". Selected text is used as context; with nothing selected the AI writes from scratch. (#230)
- Hold send for the on-device model — keep a single dictation on your device without switching providers: hold the send button while recording and your downloaded model transcribes it. The on-device provider now also sits at the top of the provider list. (#228)
✂️ Better transcripts
- Long pauses are trimmed — silences longer than a couple of seconds are cut out before the audio is uploaded. Every spoken word is kept; only the dead air goes, which means shorter uploads, less waiting and lower cost. (#232)
- Automatic paragraphs — long dictations no longer arrive as one wall of text. Set a word count and Dictate starts a new paragraph at the next sentence end. Deterministic, and only for plain transcripts, so AI-formatted text is never second-guessed. (#225)
- Smart Turn v3 for long-form — long-form dictation can now use an optional on-device model to cut at finished thoughts instead of at every pause. (#191)
- No more prompt echo — on silence or unclear audio, Whisper-style models used to echo their style prompt back ("This sentence has capitalization and punctuation."). The default prompt was replaced with a natural example in every language, and any echo is now detected and dropped instead of being inserted. (#77)
🎨 Interface
- Cloud orb — a fourth skin for the floating button: a soft cloud that grows and swirls with your voice and shows every stage (listening, thinking, done), plus a reactive dot on the keyboard.
- Floating button improvements — it responds instantly, no longer flickers while the timer runs, and can optionally copy every dictation to the clipboard as a safety net. (#214, #231)
- History panel — opens noticeably faster (the list is rendered lazily) and shows a proper loading spinner.
⌨️ Typing
- German autocorrect — restores umlauts and ß (
fur→für,weiss→weiß) and surfaces ordinary spelling fixes, plus apostrophe restoration for English contractions (whats→what's). (#219, #212) - Shift cycles capitalization of the current selection.
- Arabic 2 layout (Gboard-style) and a Dutch glide-typing dictionary.
⌚ Wear OS (5.2.0-w3)
- Watch dictation survives dropouts — the phone can no longer cancel a transcription mid-flight, the transcript is delivered with retries instead of fire-and-forget, and the watch retries the Bluetooth transport.
- A failed dictation no longer loses your recording — it's kept, and the error shows "tap to retry" to re-send that exact audio.
- Real error messages — the provider's actual error is shown on the watch instead of a generic "Transcription failed". (#218)
🔋 Under the hood
- The screen stays awake for the whole dictation — the flag is now held at window level, so opening a panel mid-dictation can't drop it and let the screen time out. (#231)
- On-device models free their memory when idle — a Parakeet model can hold ~700 MB; it's now released after an adjustable idle timeout and on system memory pressure.
- Fixes — OpenRouter connection stalls, microphone released properly after recording, accent long-press no longer flips the classic swipe layout (#221), realtime audio preserved during provider handshakes.