DevEmperor Release Notes

Dictate 6.1.1 is a bugfix release, and it installs the way a bugfix release should: no what's-new tour, no update notice, nothing to dismiss.

🐛 Fixed

Opening the GIF panel could take the keyboard down. (#307) KLIPY sometimes returns the same GIF twice within one page of results. The grid identifies its tiles by that id, and a repeated one throws out of Compose's measure pass — which kills the keyboard mid-sentence, in whatever app you were typing in. Results are now deduplicated as they arrive, on the first page as well as on every page scrolled in after it. Present since 5.1.0.

A fresh install is no longer made to catch up on every past release. Nothing is shown when you first install, because there is nothing to catch up on — but that also meant the "already seen" mark was never written, and the next update, whichever one it turned out to be, replayed all six what's-new tours back to back and opened a changelog listing every release since 5.0.

A patch release no longer announces itself. The changelog dialog, the "Dictate was updated" notice on the keyboard and the floating-button spotlight are tied to feature releases now, not to every version number. Skipping 6.1.0 and landing here still shows you what 6.1 brought.

If 6.1.0 has been working for you and you don't use the GIF panel, there is nothing in this release you will notice. That is the intention.

Dictate 6.1.0

Dictate 6.1.0 is a release about the things you do around dictating. Point the keyboard at a folder and it becomes a sticker panel. Share a voice message to Dictate and it tells you what it says — no field to find, no button to press. And the autocorrect finally catches the ordinary typo, the one it was built not to see. Updating shows a new What's-new tour for 6.1; every tour stays re-viewable under Settings › About.

🖼️ Your own stickers (#280)

Point Dictate at a folder and its pictures become stickers. Subfolders turn into tabs, each with its own favourites and recents. No account, no catalogue, no upload — the folder is the feature.

Add one from any app through the share sheet, and delete one without leaving the keyboard.

What a chat app accepts is not what it says it accepts. WhatsApp asks for image/webp.wasticker and never plain image/webp, then validates what arrives under that name and answers an oversized sticker with an empty frame; Signal takes an animated WebP and shows a single frame of it. So each sticker is brought into one shape — 512×512 WebP within budget — once, on the way into the folder, and inserting is a lookup and a commit.

Two derivatives cover the rest: a PNG for an app without WebP, and a GIF, written by hand because Android cannot encode one, for an app that would otherwise freeze the animation.

🎧 Share a voice message to Dictate (#301, from #300)

Dictate is now in the share sheet for audio and video, with Open with from a file manager as well. Share a voice message and a screen opens that starts transcribing by itself: sharing a file to a transcriber has already said what should happen to it, and a second button would be a toll on a decision made twice.

File transcription has existed since 4.0.0, but only ever answered one of the two questions people have about an audio file. Long-press the mic and the text lands at the cursor — put this file's words into the field I am typing in. What someone actually does with a voice message is the reverse.

Long recordings are handled in pieces rather than turned away, the transcript is searchable, and the player has fixed ends and a real position.

One entry per file, on a screen you can come back to.

✍️ Autocorrect (#295, #150)

The typo it was built not to see is fixed. The rule deciding whether a correction could be swapped in silently let through a finger that had slid 90% of the way to the next key — but never one that landed on the neighbour squarely, and never a word with two slips at all. That is the ordinary typo, and it now gets corrected.

How eagerly it corrects is a setting, measured against two populations rather than one: how many real slips get fixed, and how many correctly typed words get damaged. Both numbers are in the repository as a test that stays.

The word space is about to take is marked, in your accent colour, in every bundled theme. It had been handing the strip an "auto-commit" attribute since #150 that no stylesheet ever read.

Backspace right after a correction gives back what you typed, the way Gboard and SwiftKey do.

👤 Contacts, without the address book (#264, #263)

Your contacts' names can go into the personal dictionary, so the keyboard stops underlining them and starts suggesting them — through a picker, or by importing a vCard.

It never asks for READ_CONTACTS. You hand over the names you want; nothing else is read.

A word you added now competes for the strip instead of owning it. With a handful of hand-added words the old behaviour was invisible; after importing a contact list it is not.

🎙️ Dictation providers

Gemini transcribes with models built for it. (#292) Google shipped gemini-3.5-transcribe and gemini-3.5-transcribe-live on 26 August; until now Gemini transcribed with its multimodal chat models under a stern instruction to return the words and nothing else, and streaming was off altogether.

Deepgram Flux, live. (#291) Flux decides for itself when a turn has ended instead of waiting out a silence timer. It is streaming-only and lives on a different API version, reporting turn events rather than results — so picking it used to fail either way round.

Say which languages you speak, not just one. (#99, #248) An expected-languages list for the models that accept one, and free detection no longer turns into a failed dictation over a region tag.

A model that only thought gets asked again, with the thinking turned down. (#304) A rewording that came back empty because the budget went entirely on reasoning used to replace a dictation with nothing.

A failed dictation says which half failed. (#284) A rewording that died reported "unknown error during transcription", and on the normal path said nothing at all — the raw transcript appeared and the rewording was silently gone.

⌨️ Typing & layouts

Russian can be typed phonetically (#302) — a ЯШЕРТЫ layout beside ЙЦУКЕН.

French finds its accents from the plain letters (#306) — ho reaches hôte and hôtel, oeu reaches œuvre, and an unaccented spelling still gets its accent restored.

Prompts can be triggered by typing a shortcut (#283), not only by tapping one in the strip.

The suggestions switch really switches suggestions off (#297) — a disabled child preference kept running underneath it. And an app can no longer switch your suggestions off without you (#296): the flag that asks for it used to kill completion and autocorrect outright. Password fields are still refused, in code.

Emoji suggestions are no longer switched off by something else. (#298)

A deleted community prompt can be added back. (#303) The library reported prompts as already added that existed nowhere.

🔧 Fixed

Very wide screens get a keyboard again. (#114) In a window 1600dp or wider — a 14.6" tablet in landscape, DeX, a desktop-sized window — the baseline every keyboard dimension is a fraction of was 0 × 0, so the window collapsed to nothing.

Autofill chips no longer take the keyboard down with them. (#287)

Rotating the screen no longer throws away a floating-button recording. (#293) The keyboard now ends only the dictations it owns.

An error's details can be read without the keyboard ducking out from under it. A focusable popup raised by an input method takes focus off the field, so the system hides the keyboard — which tears down the popup, which brings the keyboard back.

The strips above the keys keep their own scrolling. (#188, #221, #290)

A transcript with no words in it no longer gets a conversational reply instead of a result. (#124)

Dictate 6.0.0 adds a second way in: buy credit instead of bringing your own API key. Your own key — and your own server, and models on the device — keep working exactly as before and remain the cheaper path; nothing about the app requires the new one. Alongside that: Chinese typed the way it is actually typed, seven languages that had no dictionary at all, emoji search in over forty languages, and recordings that cost less to transcribe. Updating shows a new What's-new tour for 6.0 — and every tour stays re-viewable under Settings › About.

☁️ Dictate Cloud (optional)

Buy minutes instead of finding an API key — four prepaid packs through Google Play (150, 400, 1000 and 2200 minutes; the larger ones cost noticeably less per minute, and the app shows by how much). Dictation and rewording then run through our server.

Nothing of yours is stored there. Neither your recordings nor your text are written to disk: they are passed straight to the provider and the answer comes back. What is kept is numbers — wallet id, timestamp, duration, token counts, status code, milliseconds.

The server's source is in this repository, under cloud/. The privacy policy makes claims about that server, and a claim you can read the source of is worth more than one you have to take on trust. cloud/src/meter.ts is the only file that writes anything.

No name, no email address. An account is a wallet and a recovery code, so it can be restored on a new phone — and deleted from inside the app, with what deletion leaves behind stated plainly.

Credit is seconds, and every service prices itself into them. That is the safety property rather than a simplification: a pack's price is a hard ceiling on what it can cost to serve, whatever you spend it on.

A warning before the credit runs out, a top-up button when it does, and a refusal before the microphone opens rather than after the upload.

💸 Cheaper, and no longer too long

Recordings can be sped up before upload, without your voice going higher. (#272) Most providers bill by audio length, so a recording a third shorter costs a third less. Off by default, and the row says what it is set to.

Long dictations get packed as AAC instead of being refused. (#281) Every provider's documented upload ceiling is recorded now, so the decision is made against the real limit rather than one guessed number for everybody.

Hold stop to take back a transcription that is hanging. (#270) An on-device run shows as a mark on the status rather than as a different status.

🇨🇳 Chinese (#262)

Pinyin input with a candidate row — until now the only Chinese IME was Zhengma, which hardly anyone uses. The dictionary pack downloads on demand.

SenseVoice Small on the device — an offline model actually trained on Chinese, Cantonese, Japanese and Korean, rather than a general one asked politely.

SiliconFlow as a transcription provider, reachable from mainland China.

The Chinese table is no longer scanned end to end on every keystroke, and a subtype whose table has not arrived yet says so instead of reporting itself as missing.

⌨️ Typing & languages

Seven languages gained a word list (#265) — Arabic, Bengali, Finnish, Hindi, Indonesian, Tamil and Urdu now get suggestions, spell check and autocorrect.

An Arabic word is found however it was spelled — normalised across alef, ya and ta marbuta and with diacritics ignored — and the strip stops answering with English.

Icelandic and Georgian contained the wrong languages entirely and were rebuilt. Devices already holding the broken copy get the corrected one.

Long-press characters in 19 more layouts now follow what the language actually writes, measured from real text rather than assumed. Portuguese vowels corrected (#279), and the Rusyn і key no longer offers ѣ twice, once under a Latin label.

Glide typing knows the words you added yourself. (#263)

Next-word prediction fires after a promised space too, not only after a real one. (#266)

Each dictionary is now kept strictly to its own script.

😀 Emoji & GIF

Emoji search in 51 languages. (#274) It knew six. Search for "heart", "心" or "قلب" and you land on the same emoji; the search follows your keyboard's language.

GIF search sits on the same bar as the emoji search — recents while idle, one clear button instead of two, and the caret on the left.

A swiped word reaches the search box it was typed into.

🎈 Floating button

It reads back what the input connection cannot report (#277), so it no longer flashes a green check over text that never landed.

Auto-enter aims at the right field and admits when it was refused. (#278)

It goes down with the screen instead of surviving onto the always-on display. (#269)

One refused character no longer condemns the whole dictation — the text is handed back rather than thrown away.

🎙️ Dictation & rewording

Rewording no longer translates unbidden. (#268, #276) The output language is anchored to the text, not to the language the instruction happens to be written in.

Croatian is no longer primed with an English sentence (#275), and the mic button no longer needs a second tap (#261).

When a recording never reached a provider at all, the error points at the offline engine instead of shrugging.

The crash right after updating is fixed. (#267) The floating button asked the Android version whether it could use a shader, when the question was whether this frame would reach a GPU.

🔧 Setup & your own provider

The setup wizard names four ways in, not two. (#273) On-device models download straight from the wizard — the two that fit your language, not all twenty-one — and "your own server" hands off to the editor that already existed. A keyless self-hosted endpoint no longer reads as "not set up" while dictating happily.

The Ollama editor now says it has no speech-to-text endpoint, and names both ways on.

The README has a worked self-hosting example, including the two things people trip over: the trailing /v1/, and that localhost means the phone.

Onboarding rebuilt around its illustrations; the step counter no longer jumps between steps.

🔒 Security & privacy

A private way to report a vulnerability — a SECURITY.md and GitHub's private advisory form, so a security report no longer has to start life as a public issue.

The privacy policy was rewritten for Dictate Cloud, the transcription history and GIF search.

🔋 Under the hood

An extension load no longer races against itself and deletes the cache another load is reading from. (#282)

x86_64 is shipped as well, so the app installs on emulators.

Around a dozen new test suites — audio encoding and its cost, the speed-up, the dictionary languages, the Chinese subtypes, the popup mappings, the provider-configured rule and the credit-pack savings.

Thank you to everyone who filed an issue, sent a mail or left a review — nearly every line above started as one of those. 💙

Dictate is distributed via the Google Play Store.

Downloadable keyboard language packs (.flex extensions), fetched on demand when a subtype that needs one is added. Not part of the APK.

Chinese Pinyin — net.devemperor.dictate.pinyin.flex

The reading table behind the Chinese (Simplified) — Pinyin subtype (issue #262). Built by tools/pinyin-dict/generate.py:

• Readings from CC-CEDICT (MDBG), CC BY-SA 4.0 — the generated table is a derivative and carries the same license.
• Ranking from the OPUS OpenSubtitles zh_cn frequency list.
• Words the dictionary does not list get their reading composed from per-character statistics learned from CC-CEDICT itself (98.8% accurate under leave-one-out).
• Full sources and rationale: tools/pinyin-dict/ATTRIBUTION.md.

Per-language glide-typing word dictionaries (issue #127), downloaded on demand by the keyboard.

Sources / attribution

Word frequencies: OPUS — OpenSubtitles (https://opus.nlpl.eu).

Casing & spell-filter (build-time only): Hunspell + wooorm/dictionaries (https://github.com/wooorm/dictionaries), each dictionary under its own licence. he and is are built OPUS-only (their Hunspell dictionaries are AGPL / CC-BY-SA).

Details: tools/glide-dict/ATTRIBUTION.md.

English and German ship bundled in the app; every other language downloads from here. Build tooling: tools/glide-dict/.

Dictate 5.3.0 is about the two things you do most: talking to your phone and typing on it. The mic key can now be held like a voice message, autocorrect was rebuilt to read where your fingers actually land, on-device models write while you speak, and 45 languages that had been missing are back. Updating shows a new What's-new tour for 5.3 — and every tour stays re-viewable under Settings › About.

🎤 Push to talk

Hold the mic, release to send — like a voice message: hold the mic key and talk, let go and it goes. Slide left to throw the recording away, drag up to lock it hands-free. A quick tap still starts a recording the way it always did, so nothing you already knew stops working. Opt-in under the Dictate settings. (#235)

The held mic grows out of the key it replaces without jumping, keeps its centre wherever the key sits, and behaves the same with or without the rewording row. It works in real-time mode too, and it deliberately stays out of the classic keyboard-free layout, where the record button already owns the press.

⌨️ Typing

Autocorrect, rebuilt — corrections are now decided from the touch coordinates, searching the likely words with a beam search as you type, instead of guessing from the finished word. On our test set that moved accuracy from 88.4% to 97.9%; the difference shows up most on fast, sloppy typing. (#242)

German nouns are capitalised even when typed in lowercase. (#242)

Next-word prediction — the suggestion strip offers what usually comes next, learned from how you write, and any word can be added to your dictionary with a long press, so names and jargon stop being corrected. (#241, #245)

📴 Offline

On-device live transcription — downloadable streaming models transcribe while you speak rather than only when you finish, in ten languages (English, German, Spanish, French, Italian, Dutch, Portuguese, Swedish, Turkish and Hebrew). (#233)

Two new one-shot models — Canary 180M Flash covers English, German, French and Spanish in 207 MB, under a third of Parakeet's footprint at comparable accuracy, and GigaAM v2 is specialised in Russian. (#255)

The on-device attributions screen now covers every shipped model.

🌍 Languages

45 languages added — Croatian, Bengali, Swahili and 42 more. The catalog had gaps that had nothing to do with what the providers actually support; it is now built from what they can really do. (#252)

🎨 Interface

Two new floating-button designs, both alive rather than illustrated: Aurora (light moving inside a sphere, its temperament set by what the app is doing) and Lattice (a sphere of dots that wires itself together while idle, ripples with your voice, and twists while your text is reworded — a faithful port of thinking-orbs). Both follow your accent colour. (#253)

Every design now has the same footprint, the same distance to the screen edge whichever way it got there, and a cancel button cut from its own surface instead of a stock grey circle. (#253, #88)

Every provider carries its own logo in the settings instead of a generic cloud.

The recording indicator can be still, pulsing or voice-reactive. (#238)

Settings dialogs keep a persistent scrollbar and stop content from sliding underneath it.

🔌 Providers & your own server

OpenAI's gpt-transcribe and gpt-live-transcribe are supported, and the realtime model picker is back. (#248)

A server of your own can stream too — if it speaks the OpenAI realtime protocol under /v1/realtime, live transcription runs against it. (#249)

Wake a sleeping server — for the common self-hosting shape of a small always-on box in front of a GPU machine that sleeps, Dictate can send a throwaway request the moment a rewording is certain, so the machine has the whole dictation to boot in. Per-server and off by default. (#189)

Provider fields show the effective model instead of an empty box. (#248)

📝 Output

Prompt output can keep the original transcript beside it, so a rewording never costs you what you actually said. (#240)

Paragraphs stop breaking after abbreviations, ordinals and initials. (#239)

⌚ Wear OS (5.3.0-w4)

The watch settings no longer open the system keyboard switcher, whose text is clipped on a round display; the single remaining keyboard entry goes straight to the system input-method settings. (#106)

🔋 Under the hood

Holding the mic and sliding no longer flips the classic layout out from under a running recording. (#235, #125)

A push-to-talk hold survives the moment Compose ends its own pointer dispatch mid-press — the gesture is driven from the window's touch stream instead.

On-device model selection can be tapped by name, not just by its radio button.

All on-device models

Dictate downloads at runtime, mirrored in one place so the app never depends on a third party while you are dictating. Nothing here ships inside the APK — you pick what you need in Settings → Providers → On-device, and audio never leaves your phone either way.

Every model is int8-quantised and converted to ONNX by the sherpa-onnx project (Apache-2.0). Each upstream license permits redistribution; see NOTICE.

Live / streaming — types while you speak (#233)

kroko-* — Kroko ASR community models by Banafo (CC-BY-SA), streaming Zipformer2 transducers. These drive on-device real-time transcription: text appears in the field while you are still talking. They emit punctuation and capitalisation natively.

Model
Language
Size

• kroko-de-*
  German
  ~71 MB

• kroko-en-*
  English
  ~71 MB

• kroko-fr-*
  French
  ~71 MB

• kroko-es-*
  Spanish
  ~156 MB

• kroko-it-*
  Italian
  ~156 MB

• kroko-nl-*
  Dutch
  ~156 MB

• kroko-pt-*
  Portuguese
  ~156 MB

• kroko-sv-*
  Swedish
  ~156 MB

• kroko-tr-*
  Turkish
  ~156 MB

• kroko-he-*
  Hebrew
  ~156 MB

German, English and French use sherpa-onnx's own published conversion — a leaner re-export that is both smaller and more accurate than the upstream build. The rest are extracted verbatim from Banafo's .data containers, which is why their encoder is larger and decodes roughly 1.5–2× slower.

One-shot — transcribes after you stop

parakeet-tdt-0.6b-v3-* — NVIDIA Parakeet TDT 0.6B v3 (CC-BY-4.0), 25 European languages, ~670 MB. The most accurate all-rounder.

parakeet-primeline-de-* — primeline German fine-tune of the above (CC-BY-4.0), ~670 MB. Substantially better on German than the base model.

tiny/base/small-* — OpenAI Whisper (MIT), 99 languages. Base (~153 MB) is the recommended default. The *.en variants are English-only and lighter for the same accuracy on English.

Supporting models

• silero_vad.onnx — Silero VAD (MIT). Splits long audio at speech pauses and powers "skip silent recordings" (#93).

• smart-turn-v3.2-cpu.onnx — Smart Turn v3 semantic turn detection, used by long-form auto-split (#191).

Filenames are referenced directly from LocalModelCatalog.kt with pinned sizes and SHA-256 checksums, which the app verifies after every download. Renaming or replacing an asset here breaks installs in released app versions — add new files instead.

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.

Dictate 5.1.0 builds on the 5.0 milestone with a transcription history, long-form dictation, GIF search and a big classic-layout upgrade. Updating from 5.0 shows a new What's-new tour for 5.1; coming from an older version, you'll get the 5.0 tour first and then 5.1 — and every tour stays re-viewable under Settings › About.

🎙️ Transcription & AI

• Transcription history — every dictation is kept in a searchable history. Re-insert a past transcript with a tap, replay the original audio, re-transcribe it, or pin the ones you reuse; a dedicated screen manages everything, including how long audio is retained. (#140)
• Long-form dictation — speak for as long as you like. Long recordings are split into segments and transcribed in the background as you go, so you get your text sooner and never hit a length limit. (#170)
• German offline model — Parakeet German (primeline) transcribes entirely on-device, no internet needed. (#176)
• Claude (Anthropic) joins as a new provider for rewording and formatting your dictations.
• Model downloads run in the background — on-device model downloads keep going when you close the dialog or leave the app, with an ongoing progress notification. (#207)
• Pick the active transcription language directly in settings. (#174)
• The stop button now truly cancels an in-flight transcription or rewording — no more paying for a request you've already stopped. (#192)
• A custom reasoning-effort value for rewording, and it's dropped gracefully when a model doesn't support it. (#186, #184)

⌨️ Keyboard & layout

• GIF search — a fast, Gboard-style GIF picker built right into the keyboard. Search and drop a GIF straight into your chat.
• Classic layout, reworked — a freely arrangeable action row you build by drag & drop, long-form recording controls, one or two prompt rows, an always-available backspace, a character popup on the Enter key, and an optional second "switch keyboard" button for easier one-handed use. (#183, #194, #196, #206)
• Multilingual typing — bilingual users are no longer autocorrected across languages. (#190)
• A show/hide toggle for API-key fields. (#195)

🔧 Settings & polish

• In-app settings search — find any setting by name, jump straight to it and highlight the row. (#187)
• The classic dictation layout now has its own settings category. (#199)

🐛 Fixes

• A malformed (third-party) theme can no longer crash the keyboard with a NaN text size.
• The emoji, clipboard and history panels now keep the keyboard's exact height, so they don't jump when opened.
• The Smartbar "Switch language" button cycles your layouts instead of jumping to another keyboard app. (#200)
• Classic number pad: multiple digits no longer overwrite each other, and the backspace key has the full delete gesture.
• Space/backspace swipes are preserved on the modern keyboard in the legacy swipe mode. (#188)
• Startup crash fixes, a loading indicator for the history panel (#205), shorter settings labels that no longer get cut off (#202), and various smaller fixes.

Dictate 5.0.0 is the biggest update since 4.0 — the first time you open the app after updating, a new What's-new tour walks you through the highlights and drops you straight into each setting.

⌨️ Keyboard & typing

• Glide typing — swipe across the keys to type whole words, with per-language dictionaries that download on demand. (#127)
• Word suggestions, spell check & autocorrect — on by default, with SwiftKey/Gboard-style ranking (keyboard-proximity noisy-channel + bigram context across 34 languages). (#127)
• Gboard-style autocorrect UX — the auto-applied candidate is bolded and the word you actually typed stays tappable in the suggestion strip, so one tap undoes a correction. (#150)
• Classic keyboard-less "legacy" dictation layout — the pure voice screen from Dictate 3 is back: set it as your default (locked) or keep it a horizontal swipe away from the full keyboard, with number-pad + system-emoji overlays, space-swipe cursor movement and hold-backspace multi-character selection. (#125)
• Bigger emojis with tighter spacing (#148), Select-all is now a toggle that reflects the field's selection (#152), a new high-contrast E-Reader / E-Ink theme (#54), and accent auto-contrast (black text/icons on very light accent colours).

🎙️ Transcription & AI

• Real-time / streaming transcription — watch your words appear as you speak, with OpenAI, Deepgram, Soniox, AssemblyAI and ElevenLabs, including an experimental live preview even on the floating button. (#128)
• Three new cloud providers — ElevenLabs Scribe, Deepgram and AssemblyAI; OpenRouter now auto-discovers dedicated STT models. (#143, #157)
• Offline transcription — the on-device NVIDIA Parakeet TDT 0.6B model (experimental) runs with no internet and nothing leaving your phone, and a local Silero VAD silence filter skips empty recordings so you never get ghost text or waste an API call. (#154, #93)
• Reasoning-effort control for rewording calls — globally (#141) and per prompt (#155).

📚 Prompts & community

• Community prompt library — browse rewording prompts shared by others and install them in a tap, or contribute your own. (#105)

📊 Insights & feedback

• Dictation statistics — a stats screen, a home-screen card and milestones. (#142)
• Optional haptic feedback for the recording / transcribing / rewording states — on the phone and on Wear OS. (#166)

🎈 Floating button

• Far more reliable keyboard-style text insertion plus resend-on-failure, a fully custom colour, and a live realtime preview. (#156, #160, #161)

⚙️ Settings & compatibility

• Dictate settings reorganised into a scannable category hub. (#153)
• Selectable audio input source, including the new high-priority VOICE_COMMUNICATION option that keeps working when another app is holding the mic. (#62, #167)
• Trust user-installed CA certificates (#137); Ollama / self-hosted servers now allow cleartext HTTP with an editable base URL (#136).
• Instant recording can skip number-only fields (#146); Dictate offers to save the recording when a transcription fails as too large (#144).
• In-app language-data attributions (Settings → About).

⚡ Performance & fixes

• Fixed typing jank (especially on Samsung): the floating-button accessibility service no longer re-fetches the entire focused node tree on every keystroke.
• Audio-pipeline speedups: streaming Base64 encoding, a PCM resampler fast path, and fewer capture-buffer copies.
• The mic now stops when the screen turns off mid-recording. (#147)
• Crash fixes: the shared prompts database was being closed per query (#138), and an invalid inline-suggestion inflate size (#145).
• Auto-formatting no longer spills its prompt into the field on empty recognition (#124); the "keyboard not enabled" banner no longer flashes on settings open.

Wear OS-only re-release fixing the Google Play "Watch shapes" rejection of 4.3.0-w1 (version code 100124). The phone app is unchanged and stays on 4.3.0 (123).

What changed (Wear OS)

Round-display layout fix — the numbers keypad and the emoji grid filled the full rectangular width, so on circular watches their corner cells (keys 1/3/⌫/⏎ and the outer emoji columns) were clipped by the edge. Page content is now inset by the BoxInset factor (≈14.6% of the screen) so it fits inside the circle's inscribed square — nothing is cut off. Square watches are unaffected.

Verified on a round 454×454 Wear OS emulator.

Availability

Install from Google Play once the Wear OS track update is live.

Version: 4.3.0-w2 · versionCode 100125 (Wear band).

Wear OS-only re-release that fixes the Google Play review rejection of 4.3.0 (version code 100123). The phone app is unchanged and stays on 4.3.0 (123).

What changed (Wear OS)

• Functional dictation, demonstrable in-app — a new Try dictation button on the watch settings screen records → transcribes → shows the transcript right there, so dictation works without first enabling the keyboard.
• Keyboard onboarding — detects whether the Dictate keyboard is enabled/selected, with shortcuts to enable it and pick it (Dictate is an input method).
• Scrollbar — the settings list now shows the Wear scroll/position indicator.
• Full localization — all watch strings translated into the 20 maintained languages, kept short for the small screen.
• Version footer — shows Wear OS · v4.3.0-w1 (100124), explicitly Wear-labelled.

Availability

• Install from Google Play once the Wear OS track update is live.

Version: 4.3.0-w1 · versionCode 100124 (Wear band).

On-device transcription (offline)

Dictate completely offline — no internet needed and nothing ever leaves your phone.

Download an on-device speech model once, then transcribe locally

Great for privacy, flights, and spotty connections

Set it up under Settings ▸ Dictate ▸ Providers.

Wear OS keyboard

Dictate straight from your watch — tethered through your phone or fully standalone.

Voice-first input with number and emoji pages

Auto-syncs your settings from the phone; optional on-watch auto-rewording

Live waveform, swipe-down to close

Find & replace rules

Automatically fix recurring words, names or phrases in every transcript. Set them up under Settings ▸ Dictate ▸ Custom mappings.

Single-call mode

Let one audio-capable AI model transcribe and format in a single request — lower latency and often lower cost. Toggle it per provider.

Other improvements

New Smartbar actions to switch back to your previous keyboard or open the system keyboard picker ⌨️

The keyboard's accent color now follows the color you pick under Settings ▸ Theme 🎨

Optional undo button on the floating dictation button ↩️

Various fixes and stability improvements 🛠️

Full changelog: v4.2.0...v4.3.0