Changelog
v0.1.9
New Features
- Automatic history cleanup: Your history and its saved recordings can now be cleaned up automatically so they don't pile up forever. In Settings, a new "Data retention" section lets you choose how long to keep them — 7 days, 30 days (default), 90 days, 180 days, 1 year, or Never.
- The cleanup runs quietly on its own when the app starts — at most once a day — so you never have to think about it.
Behavior Changes
- History is now kept for 30 days by default. Anything older, along with its recording, will be automatically deleted the next time cleanup runs.
- If you want to keep your history and recordings indefinitely, go to Settings → Data retention and choose "Never" before upgrading, or as soon as possible after.
Improvements
- Data points on the overview chart are now narrower, giving the chart a cleaner, less cluttered look.
v0.1.8
Improvements
- The activity chart on the Overview page now adapts to its size: when you're viewing a long time range or have a narrow window, nearby days are automatically grouped into evenly sized totals instead of showing one point per day, keeping the chart readable at any width.
- Hovering over a point on the Overview chart now shows the exact day (or date range) it covers, and the chart header displays the grouping currently in use — for example "Daily" or "4-day totals".
- Chart lines now make fuller use of the chart's height by scaling between the highest and lowest values in the selected range, making trends and day-to-day differences easier to spot.
- Polished the Overview page's loading placeholders so the layout stays steady and nothing overflows while your stats are loading.
macOS
- In Settings, macOS users now see a disabled Apple-logo button in place of "Check for Updates", since checking for updates isn't available on macOS.
v0.1.7
Improvements
- More reliable text enhancement: When the AI assistant can't or won't process your text, the app now falls back to your original transcription instead of showing a refusal message — so you always get usable output.
- Cleaner results: If the enhancement step returns nothing meaningful, the app now discards it rather than inserting empty or broken text into your result.
v0.1.6
New Features
- NVIDIA Parakeet speech recognition models — In addition to Whisper, you can now use NVIDIA's fast Parakeet models for local transcription, including TDT v3 (multilingual), TDT v2, and CTC variants
- Model provider badges — Each local speech model now shows the provider icon (OpenAI or NVIDIA) so you can easily tell who made the model
- Model descriptions — Hover over any model in the selection list to see a brief description of what it does, how fast it is, and what languages it supports
- Recommended models highlight — Recommended models are now shown first in the list, making it easier to find the right one for your needs
Improvements
- Clearer model names — Models now display their full names with engine prefix (e.g., "Whisper Base" instead of "Base") and English-only models show an "(EN)" suffix to distinguish them
- Model selection UX — Downloaded models now show a checkmark icon instead of a download button; the "EN" badge for English-only models has been replaced with clearer naming
- Simplified model management page — The local models page has been redesigned with a cleaner card layout and more accurate size display
Bug Fixes
- Parakeet models now correctly unavailable on Intel macOS — Parakeet models are properly hidden on unsupported platforms instead of showing an error after download
- Fixed "Large v3 Turbo" display name — The model now displays as "Large v3 ⚡" consistently across all screens
- English-only models auto-set language — Selecting an English-only model now automatically switches the profile language to English
v0.1.5
Bug Fixes
- Fixed the recording overlay not properly reappearing when activated while already active. Previously, if the overlay was already showing and needed to be redisplayed (such as when starting a new recording while one was in progress), it would silently skip updating. The overlay now correctly repositions and re-shows itself in these cases.
v0.1.4
No notable changes in this release.
v0.1.3
Improvements
- Overlay now displays on top of more windows: The overlay panel has been upgraded to a higher display priority level, ensuring it stays visible on top of system dialogs, pop-ups, and other floating windows — not just menus. This means the recording status overlay will no longer be hidden behind other on-screen elements.
v0.1.2
Bug Fixes
- Fixed the overlay window display on macOS to ensure it appears correctly above other windows.
- Fixed a layout issue where extra empty space was being reserved next to scrollable content, even when scrollbars were not visible.
v0.1.1
Improvements
- Grammar correction now better preserves your original meaning — The AI text fixer has been refined to focus specifically on fixing grammar and spelling without altering the intent or tone of your text.
- Cleaner output from grammar correction — The corrected text is now returned as plain text only, with no introductory phrases like "Here is the corrected version" and no extra formatting or explanations. You'll get just the fixed text, nothing else.
v0.1.0
New Features
- Regex-based snippet matching — Snippets now support regular expressions alongside simple literal text matching. The snippet configuration dialog has been redesigned with reorderable matchers, a type selector (literal or regex), optional regex flags, and live validation against your full snippet list.
- New "Basic" enhancement preset — A new formatting option called "Basic" focuses on fixing grammar and spelling only, without changing tone or style. It appears alongside the existing Normal, Prompt, Email, Formal, Casual, and Romantic presets.
- Profile edit and delete from the sidebar — You can now rename or delete any profile (except the Global profile) directly from the sidebar, without navigating to the profiles page.
- App-based profile auto-selection ("Default for apps") — Each profile now has a section where you can assign specific applications. When a matching app is focused, that profile is used automatically without pressing a hotkey. You can add apps directly from the profiles card view.
- System tray theme support — The tray menu icons now match your operating system's light or dark theme and update automatically when the theme changes.
- Profiles page redesign — The profiles list is now a card grid showing the formatting preset, hotkey shortcuts, and associated apps (with their actual icons). You can add apps to a profile right from the card.
Improvements
- Recording continues when the active window is unavailable — If the app can't detect which window is focused (e.g., due to missing OS permissions), recording now starts gracefully instead of showing an error.
- Smoother startup — The onboarding status check now loads asynchronously, eliminating a brief flash on startup.
- Invalid snippets are silently cleared — If your snippet configuration is corrupted or uses an incompatible format, it is automatically reset rather than causing errors.
- Tray menu cleaned up — The tray menu now has a separator between items for clearer visual separation.
Breaking Changes
- Cloud LLM-based transcription removed — The option to use a large language model directly for speech-to-text in cloud mode has been removed. LLMs are now only used for text enhancement after transcription. If you were using an LLM for cloud transcription, you'll need to select a dedicated speech recognition (ASR) model instead.
v0.0.132
No notable changes in this release.
v0.0.129
No notable changes in this release.
v0.0.127
New Features
- Translate your text into 100+ languages. A new "Translate" option is now available in the formatting choices. After picking it, you can choose a target language from a searchable list (each with its flag and native name) — from English, French, and Spanish to Swahili, Cantonese, and Hawaiian. You can search for a language either from the quick pop-up or the full picker window.
- Recent items in the system tray. The tray menu (notification area icon) now shows your 10 most recent results. Click any entry to copy its text straight to your clipboard — no need to open the app.
Improvements
- The tray menu now has an "Open OiPer" option instead of the old Show/Hide toggle, so it always brings the app window forward when you need it.
- Tray recents stay up to date. The list of recent items in the tray refreshes automatically as you generate new results, retry past ones, or delete history, so it always reflects your latest activity.
v0.0.126
Improvements
- On macOS, clicking the app's icon in the Dock now brings the main window back to the front (restoring it if it was minimized or hidden).
v0.0.125
No notable changes in this release.
v0.0.123
Bug Fixes
- The setup status panel now updates immediately when a speech model download starts, fails, or is cancelled — previously it could keep showing stale warnings until the next refresh.
Improvements
- While a speech model is downloading, the status panel now shows it as "downloading…" instead of warning that the model is missing.
v0.0.122
New Features
- Linux x64 support — The app is now available for Linux (x86_64) users. Install packages are provided in deb, rpm, and AppImage formats, with all system dependencies handled automatically.
Bug Fixes
- Overlay window now interactive on Linux — The overlay window no longer ignores cursor events on Linux, so you can click and interact with it normally. Behaviour on Windows and macOS is unchanged.
- Error messages no longer show macOS‑only instructions on other platforms — If the global hotkey listener fails, the error message will only suggest granting Input Monitoring permission in System Settings when you are on macOS. Windows and Linux users will see a cleaner message without irrelevant steps.
- Hotkey configuration on Linux uses the correct platform‑specific keys — Hotkey hold, toggle, and auto‑submit settings are now properly stored under
hotkeyHold.linux,hotkeyToggle.linux, andautoSubmit.linux, matching the pattern already used on macOS and Windows.
v0.0.121
Now I have a thorough understanding of all the changes. Let me generate the release notes.
Improvements
-
Smoother handling of empty or silent recordings — When a recording results in an empty transcription (silence, background noise, or only non-speech markers like
[Music]), the app now silently skips it instead of showing an error. This means fewer false alerts and a cleaner experience. -
Cleaner text enhancement output — The AI model used for rewriting or improving text now follows stricter output rules: it no longer adds introductory phrases such as "Here is the rewritten text" or "Sure, here's the improved version". The output is just the text itself, with no preamble.
Bug Fixes
- Fixed empty transcription errors for cloud services — Cloud speech-to-text services (both ASR and LLM-based) sometimes returned empty or meaningless results. Previously these would cause an error; now they are handled gracefully and simply ignored.
v0.0.120
Improvements
- More accurate processing time display – Processing time is now calculated by summing the actual durations of each processing step (resampling, context collection, transcription, enhancement) rather than using a simple start-to-end difference. This gives a more precise and reliable reading of how long each stage took.
- Better duration formatting for short times – Durations under one minute now display seconds with one decimal place (e.g., "1.5s") instead of showing "0m 0s", making them easier to read and compare at a glance.
- Total time in overview now includes processing – The overview cards and chart now account for processing time alongside recording time when showing total duration, providing a more complete picture of how long each session took overall.
v0.0.119
No notable changes in this release.