August 23rd, 2026
This one is about accuracy and about getting out of your way. Vowen now learns the misspelled words you correct instead of getting them wrong forever, reads names off the screen you are dictating into, and lets Ask AI edit the note you are looking at. Enhancement is a lot faster, four settings pages were rebuilt, and a run of dictation bugs that quietly ate or duplicated your words are fixed.
New
A dictionary that learns from your corrections (Pro) - Fix a word Vowen got wrong and it offers to remember it. A name it has never seen is offered after one sighting; a recurring mishearing has to be seen twice before it becomes a permanent correction, and a no is remembered for good. Switch on "Auto-add corrections to Dictionary".
Names spelled the way they appear on screen (macOS, Beta) - Names and product terms the recognizer spells phonetically are usually written correctly somewhere in the window you are dictating into. With AI enhancement on, Vowen now reads them out of the focused window through Accessibility. No screenshots, no second model call, and never a delay to your dictation.
Ask AI can rewrite the note (Pro) - Ask for a tighter summary or a better title and Ask AI applies it to the note in front of you, with an Undo. The transcript stays read-only.
Ask AI in meetings without live transcription (Pro) - Live Ask no longer needs a streaming engine, so local Whisper, batch cloud models and Windows Parakeet can use it too. Vowen transcribes only the part of the meeting it has not seen yet, when you ask a question or press Catch up. Two questions ten minutes apart cost one transcription of those ten minutes, not a re-run of the whole meeting.
Claude Code and Codex as summary writers - If you already have the claude or codex CLI installed and signed in, it shows up as a provider for meeting summaries. No API key to paste, and the subscription you already pay for does the work.
Find and replace in summaries - Cmd+F (Ctrl+F on Windows) searches the summary editor and Cmd+Shift+F opens the replace row. Replace All commits as one transaction, so a single undo puts everything back.
Cmd+1, 2 and 3 on a note - Jump straight to Summary, Transcript or Ask AI. The chords read the physical key, so they still land on AZERTY.
Dictations stay out of clipboard history - Clipboard managers like Maccy, Raycast and Ditto no longer collect every dictation you paste. There is a switch in Developer settings if you would rather they were recorded.
A get-started checklist - A pill in the corner of settings tracks the six things worth setting up first and takes you to each one. It ticks off what you have already done rather than asking again, and retires itself once you finish.
Improved
Enhancement that keeps up with you - Gemini 3 models were running with thinking on by default, which cost around nine seconds a dictation and cut long ones short: a 305-word dictation came back at roughly half its length. Thinking is now floored per model family, measured 6.9x faster and more faithful. Alongside it, OpenRouter routes for latency instead of price, reasoning models on Cerebras get a low effort budget, and the enhancement prompt itself is 18% shorter with nothing taken out of it.
Workflows, rebuilt - The workflows page is rebuilt around what a workflow actually does, trigger phrase then action, with real logos for the sites you search and browser and profile pickers in line.
Connectors, permissions and sync - Three more settings pages rebuilt on shared components. Connectors says what each one can do before you connect it, Permissions says what is missing and how to fix it, and Sync says what it last did and when.
Pages that say what they are for - The meeting-notes and transcribe pages now lead with the apps and file types they work with, so it is clear what to point them at before you have any notes or any files.
The Pro screens - Free and Pro share one card design across Account settings and the upgrade modal, and activating a licence now gets a proper thank-you screen instead of a modal that closes.
These release notes - The What's New window was rewritten. It leads with the highlights, keeps the full list of the current release below them, and collapses every past version into a row you can open, instead of one long scroll back to 0.2.8.
Fixed
ElevenLabs losing, or doubling, a dictation - A commit the server refused was treated as fatal and threw away the whole transcript, and a late partial could paste your dictation twice. Both are fixed.
The last few words going missing - Stopping a dictation could close the stream before the engine had finished. AssemblyAI, ElevenLabs and the Gemini live models now wait for the flush to be answered.
The first word lowercased in Outlook, Teams and Gmail (Windows) - A caret in an empty compose box looked like the middle of a page, so smart spacing lowercased what followed. Context is now clamped to the focused field.
Full stops eaten at the end of a sentence - Smart spacing dropped your terminal punctuation whenever anything sat to the right of the caret, including Send and Reply buttons. It now checks that the text actually continues the sentence.
Dictations ending in a dash - Speech that trails off comes back terminated with a dash. That now becomes a full stop, while dashes inside your text are left alone.
The get-started checklist ticking itself, and ticking late - "Connect an AI provider" completed itself on any machine with the Claude Code or Codex CLI installed, before you had connected anything. Creating a workflow, adding a dictionary word or adding an expansion also took until some unrelated change before the step ticked. Both fixed.
Notes settings opening slowly (Windows) - Opening the meeting-notes settings re-scanned for local CLI agents every time, spawning a process per agent. It now uses the result it already has.
The meeting banner chevron - It pointed away from where the template menu opens, and clicking it while the menu was up closed and instantly reopened it.
To update, open Vowen and it will pick this up automatically, or download the latest build from vowen.ai.
August 17th, 2026
This release is mostly about meetings. There is a floating panel you can pull up mid-call to ask questions, jot context for the summary and read the live transcript without leaving the app you are in. Meeting notes can be published as a public link, summaries can cite the transcript so you can jump straight to the moment something was said, and there is a library of ready-made summary formats so you are not starting from a blank prompt. On macOS, a freeze that could lock the app seconds after launch is gone, along with a whole class of stuck-shortcut bugs. The app is also a lot smaller.
New
The Meeting Panel — Press Cmd+\ (Ctrl+\ on Windows) during a meeting and a floating panel opens over whatever app you are in. Jot context for the summary on any plan, and on Pro ask questions and follow the live transcript as it comes in. It never appears in your own screen share.
Public share links (Pro) — Publish a meeting note as a link anyone can open. The summary and transcript go; the audio, screenshots, your private notes and your Ask AI conversations stay behind. Revoke it whenever you like.
A library of ready-made templates (Pro) — Forty-four summary formats: standups, one-on-ones, discovery calls, user interviews, post-mortems, lecture notes and more. Add one and edit it however you like.
Citations in your summaries (Pro) — Switch on summary citations and every bullet carries the timestamp it came from. Click one and the note jumps to that moment in the transcript and cues the audio there.
Ask AI gets its own tab (Pro) — Notes now have a dedicated Ask AI tab with saved conversations in the sidebar, grouped by recency, renameable, and still there after a restart. The chat box sits at the bottom of every tab, so you can ask from the summary without losing your place.
Rank your microphones — Microphone choice is now an ordered list rather than a single pick. Drag your headset above your webcam above the built-in mic, and Vowen opens the highest-ranked one that is actually plugged in when recording starts.
A separate mic order for meetings — Meetings can follow their own microphone ranking, so calls prefer the desk mic while dictation keeps preferring your headset.
More than one custom server (Pro) — Add as many OpenAI-compatible speech endpoints as you want, each with its own name, URL, model and optional key. They show up as ordinary model cards when you pick a model, and Vowen checks it can reach the server before saving.
Teach the dictionary how you get misheard — Any dictionary word can now carry the ways it gets misheard. Add "cuber netties" and "kubernets" to Kubernetes and they are corrected in your dictations automatically.
Echo cancellation for meeting notes (macOS) — On speakers, the other side of the call used to get recorded twice, once cleanly and once bleeding back through your mic. Vowen now cancels it against the actual output mix, and switches itself off when you move to headphones. Needs macOS 14 or later on Apple silicon.
Tones and new notes from the idle pill — The idle pill picks up a tone switcher and a New Note button with a template picker, so you can pin a tone or start the right kind of note without opening anything. Using the Notch indicator style, the same options are drawn natively in the notch.
Tags that come with the template — Give a template a set of tags and every note it produces is tagged from the moment it starts recording.
Mic-only templates — A new "Capture system audio" switch per template. Turn it off for in-person meetings, one-on-ones and voice journals, where recording what is coming out of your speakers is just noise.
Choose the browser and profile — A workflow that opens URLs can now say which browser, and which profile within it, to use, so work links land in your work profile instead of wherever your system default points.
Find, back and forward — Cmd+F (Ctrl+F on Windows) or / focuses the search box on the notes, transcribe, history, dictionary, threads and expansions pages. Cmd+Left and Cmd+Right (Alt on Windows) step back and forward through where you have been, browser-style.
Improved
Vocabulary that reaches the provider — Your dictionary now goes through each provider's own biasing parameter, Deepgram and ElevenLabs keyterms, AssemblyAI, Speechmatics and the rest, instead of one generic prompt, and it reaches meeting notes and file transcription where several models silently ignored it before. It also used to be truncated alphabetically, so a long dictionary quietly stopped working somewhere around "C"; it now keeps what you added most recently. A few engines still have no biasing hook at all, and those now say so in the logs instead of pretending.
A much smaller download — Vowen ships a lot lighter: bundled SDKs, duplicated dependencies and unused Chromium locales cleared out. On Apple silicon the app is now about 373 MB. One model did go with it: the on-device GigaAM Russian engine has been retired, and Russian still transcribes on every cloud model and on multilingual Whisper.
Music that stops the instant you record (Pro, macOS) — Muting background audio moved off AppleScript onto the native controller, so it lands in milliseconds instead of half a second and the first words of a video no longer leak into your recording. Plugging in headphones mid-recording no longer un-silences your Mac, and a crash can no longer leave it muted.
Pausing falls back to muting (Pro) — When the app you are playing from refuses a pause, or reports nothing is playing when something clearly is, Vowen now checks the output device itself and mutes instead of quietly doing nothing.
The meeting indicator, rebuilt — A responsive level meter, an audio-reactive glow, a live status label and a red stop button that reads as stop. The meeting-detected banner now carries the meeting app's logo and a split Start button for picking a template, and the ending banner counts down instead of just appearing.
Long recordings on Gemini — Recordings past about twenty minutes used to die with an opaque "socket hang up", because the size check measured the audio before encoding inflated it by a third. They are now compressed and, past roughly half an hour, uploaded through Gemini's Files API instead of being crammed into the request, and the uploaded copy is deleted as soon as the transcript comes back.
A live transcript that reads like one — Words in flight now settle in place with a colour change instead of vanishing and re-flowing into a different block, and speech split across two emissions no longer arrives as "ch at". Long uninterrupted turns on AssemblyAI now close within seconds in the live preview instead of running on unfinalized.
Waveforms with actual shape — Meeting recordings mix your mic with system audio far below it, and the old waveform flattened the whole remote side into a one-pixel line. Existing recordings get recomputed the first time you open them.
Search your notes settings — The meeting-notes settings modal gets the search box the main settings already had. Type "obsidian" or "citations" and the matching rows surface across all five tabs at once.
Shift-click to select a range — Select one note, shift-click another, and everything between them comes along. Works on the notes and transcribe lists, and follows whatever filter and sort you have applied.
Escape means escape — Esc now closes the top-most thing and only that, so a picker over a modal closes the picker. In the tone, workflow and expansion editors it asks before throwing away unsaved changes, and on a list it clears your selection.
One scroller per page — Dictionary, Threads, Expansions, Models and Workflows now keep their banner and search bar pinned while just the content scrolls, matching the rest of the app.
Quieter chrome — Dropped the shadows from every recording surface and the mistinted focus rectangles from every clickable one.
Tones inside installed web apps (macOS) — A tone assigned to a site used to go dead the moment you opened that site as an installed app. Website rules now match inside PWAs, and installed web apps show up in the app picker.
Fixed
The freeze seconds after launch (macOS) — Vowen could lock up about two seconds after starting, with the tray icon still there, settings dead, quit dead, and force-quit the only way out. The input hook that caused it now runs off the main thread.
Every shortcut going dead at once (macOS) — Under load macOS switches off our key tap, and if it happened mid hold-to-record the recording could never be stopped, and while it was stuck every other shortcut stopped working too. It now recovers on its own within seconds instead of needing a restart.
A bare "D" starting dictation (macOS) — Stuck modifier flags could turn an ordinary keystroke into a full chord, so a plain "D" started dictation and a plain "P" started command mode. On-screen and accessibility keyboards still fire shortcuts through the path that was always safe.
Text expansion quietly switching off (macOS) — The shared input hook could be stopped out from under the text expander when something unrelated let go of it, and snippets would just silently stop firing mid-session.
The last word going missing — Trailing-silence trimming was being applied to every cloud model by accident, clipping the final word on Deepgram, ElevenLabs, Mistral and others, while Retry transcribed it correctly. Streaming models also lost the last buffer when you stopped.
Undoing a cancellation — Undo left the indicator stuck on "connecting" for the rest of the take, brought the recording back in the wrong mode so the shortcut that started it could not stop it, and dropped the tone and language you were recording with. It is also no longer offered after a hold-to-record take, where there was nothing to resume into.
The idle pill's own shortcut — Starting a recording from the idle pill made your keyboard shortcut a no-op, so the pill advertised "Hold to dictate" and then only the mouse could stop it.
Meetings recording your mic only (macOS) — On FaceTime and Phone calls, system-audio capture could attach and deliver nothing but silence, so you would find out afterwards that the other side was never recorded. Vowen now notices within seconds and switches to a different capture path mid-recording.
Meeting notes ignoring your settings — An auto-started meeting could resolve its settings before they had finished loading, so "Identify Speakers" silently stopped applying and the model, language and template fell back to defaults.
Summaries using the wrong provider — Picking a summary provider that was not connected silently fell back to a different one, so you kept seeing an error from a provider you had not chosen. It now tells you which one is not connected and where to fix it.
The indicator opening expanded — The recording indicator appears exactly where your cursor already is after clicking Start, so it read that as a hover and opened its card at the beginning of every meeting. It now waits to be hovered on purpose.
The indicator cut off mid-dictation — Dismissing a banner while still recording could tear the indicator down or shrink it until the live preview was clipped.
Speaker setup you never asked for — Starting a meeting with a cloud model and Identify Speakers on downloaded a local diarization bundle and showed a preparing banner for an engine the recording never touches.
Vowen detecting itself as a meeting (Pro) — Dictating or using command mode could raise a meeting-detected banner off Vowen's own microphone use, sometimes announcing a Teams meeting purely because Teams was open in the background.
Everything slightly too big — In the installed app the recording indicator, its card and the meeting panel all rendered about 11% larger than intended, because the zoom the layout was designed against only applied in development.
Update from within Vowen (Settings → General → Check for updates), or download the latest build at vowen.ai.
August 5th, 2026
This release is mostly about context. Vowen fitting the app, the site, and the sentence you are dictating into. Tones are rebuilt: each one now carries its own speech model, language, AI model and instructions, and can be switched on by a keyboard shortcut or by the website you are on. Dictated text now spaces and capitalises itself to match whatever is already around your cursor. Alongside that: two new on-device Nemotron models on macOS, a thousand more connectors through Composio, watch folders that turn dropped recordings into meeting notes, and a long list of fixes.
New
Tones, rebuilt
A tone is no longer just a writing style. Each one now carries its own speech model, spoken language, AI model and custom instructions, so switching tone switches your whole dictation setup rather than just the tone of the output. Tones can also be switched off individually without losing their configuration, which is useful when you want one out of the way for a while but do not want to rebuild it later.
Per-tone shortcuts
Bind a key to any tone and dictate with it from anywhere, whatever app happens to be in front. Clashes with your other shortcuts — or with another tone's — are caught the moment you record them, so you find out immediately instead of the next time you press the key. Switching a tone off releases its shortcut for everything else.
Website rules for tones
Tones can now match on the site you are on, not just the app you are in. Add example.com and the tone applies in any browser. A website rule beats an app rule, because the page you are on says a lot more about what you are writing than the fact that some browser window is focused.
Smart spacing and capitalisation
Dictated text now reads as part of the sentence it lands in. Vowen adds the separating space the caret actually needs, matches the casing of the surrounding text, and drops a trailing full stop that would orphan whatever sits to the right of your cursor. It is always on, works out entirely on your machine, and deliberately does nothing when the surrounding context is ambiguous — a wrong adjustment is far more annoying than a missing one.
Nemotron speech models (macOS)
Two new on-device models from NVIDIA — one English, one multilingual across more than 30 languages — that transcribe in real time and punctuate as they go. Download either from the model manager.
1,000+ connectors through Composio (Pro)
Connect Gmail, Google Calendar, Drive, Docs, LinkedIn and around a thousand other apps through your own Composio account, then let command mode and workflows act on them.
Watch folders for meeting notes (Pro)
A watch folder can now produce meeting notes instead of plain transcriptions. Every file dropped in is transcribed, summarised with the template you pick, and tagged, with a banner when the note is ready. Files already sitting in the folder when you add it are left alone, same as before.
Signed webhooks (Pro)
Add a signing secret and every webhook Vowen sends carries an X-Vowen-Signature HMAC, a timestamp and a delivery ID, so whatever receives it can verify the request actually came from you.
Nowhere to paste? Drag it in
When you dictate with no text field focused, Vowen no longer drops the text. A banner appears holding it, and you can copy it or drag it straight into any app.
Hold to cancel
Hold the stop button on the recording indicator to throw a take away. It runs through exactly the same discard path as the cancel shortcut, now reachable without touching the keyboard.
Find, replace and merge in transcripts
Replace one match or all of them, merge a line into the one above it — reassigning the speaker as you go — and split at the caret straight from the row. Playback speed moved into the player as well.
More mouse buttons
M6, M7 and M8 can now be bound to any shortcut, alongside the buttons that were already supported.
Improved
OpenAI's newest transcription models — Dictation and file transcription now run on
gpt-live-transcribeandgpt-transcribe, with a hint on each so it is clear which one streams and which one is cheaper per minute.Search that reaches your content — The command palette no longer just jumps to pages. It searches your dictations, meeting notes and transcriptions by what is actually in them, and the voice log has its own search box now too.
Multi-turn commands in the voice log — A command-mode conversation with several refinement turns now appears as one entry you can page through, instead of a stack of disconnected rows.
Summaries that retry themselves — A meeting summary that fails now retries automatically, and if it still cannot finish, the note tells you why instead of sitting there empty.
Bluetooth mics get time to connect — Vowen no longer declares the microphone dead after 700ms. AirPods and other Bluetooth headsets need seconds to negotiate, so the recording waits and keeps retrying rather than erroring out.
Your clipboard comes back by default — Restoring the clipboard after a paste is now on out of the box, and the snapshot and restore moved into the native writer so more clipboard shapes survive the round trip. Writes are marked transient, so clipboard managers stop logging your dictations.
App icons that are actually right — Icons are now warmed when you switch apps and cached to disk, so the recording indicator shows the correct one the instant it appears.
Faster diarization for meeting notes (Windows) — The diarization engine is prewarmed before notes need it, so speaker labels turn up without the first-run stall.
Screensaver counts as walking away (macOS) — A screensaver that kicks in without locking the screen now stops a long-running recording, and everything re-primes when it stops.
Replacements respect word boundaries — Text replacements no longer fire inside longer words, so "cat" stops rewriting the middle of "catalogue".
Local engine recovery — The local speech daemon restarts itself cleanly after a crash and handles empty results without failing the whole take. System-audio capture for meetings now restarts on its own too, with a retry budget.
Refreshed lists and pages — The notes, transcribe and history pages got a pass: consistent tag sizing, scroll fades so you can tell there is more below, a reworked transcribe modal and file picker, and clearer AI-enhanced and command-mode badges.
Live preview that keeps up (Pro) — The real-time preview in meeting notes follows along without fighting your scroll position, and tells you exactly why it is off when your model cannot stream.
Back with the keyboard — Cmd+Left (Ctrl+Left on Windows) navigates back from a note or transcription detail page.
Fixed
The recording indicator could go mouse-solid with "always on top" enabled and swallow clicks meant for the app underneath. Every overlay surface now claims only the pixels it actually draws.
Shortcuts not firing from on-screen and accessibility keyboards, where a whole chord arrives as one event carrying modifier flags rather than as separate presses. (macOS)
Vowen's keyboard-layout probe re-scanned the layout on every check and consumed pending dead keys, so an accent you had just typed vanished. It now only re-scans when the layout actually changes. (Windows)
Meeting detection could leave orphaned microphone-listener processes behind, which degraded audio system-wide until they were cleared. They are now cleaned up before spawning and on quit. (macOS)
AI enhancement could reply to your dictation instead of cleaning it, pasting something like "I don't see any transcript content to clean" into your document. Vowen now detects that and keeps your own words instead.
AI enhancement on DeepSeek returned empty results because its thinking mode swallowed the output. Thinking is now disabled for enhancement, and provider errors are surfaced rather than silently returning nothing.
Custom vocabulary sent to Groq could leak into the transcript as a prompt echo.
Meeting notes generated from a screen recording could fail outright when the AI provider was Gemini.
Picking a different model when regenerating a transcript no longer overwrites your global transcription defaults.
The title in meeting notes could revert or fail to save while being edited.
Trailing-silence trimming could still clip softly spoken final words before transcription.
Long hotkeys and long translations were cut off in the idle pill's tooltips, which now measure themselves before the window is sized.
The connectors list did not scroll when it ran past the bottom of the window.
Handle-based clipboard formats were copied by value during snapshot and restore, which could corrupt whatever was on the clipboard before a paste. (Windows)
Leftover focus juggling around selection capture and overlay windows meant Vowen could activate other apps or hide itself behind them. (macOS)
Update from within Vowen (Settings → General → Check for updates), or download the latest build at vowen.ai.
July 26th, 2026
This release brings Vowen to the terminal. There is now a proper vowen CLI, and because it speaks MCP, coding agents like Claude Code and Opencode can read your transcripts and notes and transcribe audio on their own. Alongside that: watch folders that transcribe anything you drop in them, a native system-audio engine for meeting notes on macOS, media that pauses itself while you dictate, and a rebuilt sync engine. Plenty of this came straight from your reports — thank you for sending them in.
New
The Vowen CLI
Vowen now lives in your terminal too. Transcribe audio files, browse and search your notes and dictations, and manage tags, vocabulary, and expansions from the command line. Install it with one click from Settings, or grab it yourself with curl -fsSL https://assets.vowen.ai/cli/install.sh | bash (irm https://assets.vowen.ai/cli/install.ps1 | iex on Windows).
Claude Code and Opencode integration
Run vowen mcp and any MCP-compatible AI agent can work with your Vowen data directly — reading transcripts and notes, searching your history, and transcribing audio on demand. Set it up once and your coding agent has your dictation history as context.
Watch folders (Pro)
Point Vowen at a folder and every audio or video file dropped into it gets transcribed automatically. Each folder gets its own tags and rules for what happens to the file afterwards. Existing files are left alone when you add a folder, so pointing it at your Downloads folder will not transcribe everything already in there.
Native system audio for meeting notes (macOS)
Meeting notes now capture the other side of the call through a native macOS engine instead of a screen-share stream. This is far more reliable with AirPods and other Bluetooth headsets, where the old approach could go silent or crackly when the headset switched profiles mid-call, and it is noticeably lighter during long meetings.
Pause your music while you record (Pro)
A new option pauses whatever is playing — Spotify, YouTube, anything with media controls — the moment you start recording, and resumes it when you stop. Available on both macOS and Windows.
Choose which apps count as meetings (Pro)
Decide exactly which apps trigger the meeting-detected banner. Toggle each meeting app individually, set a rule for everything else, and mute a noisy app straight from its banner.
Start notes with the right template
"Start Taking Notes" is now a split button. Start instantly with your default template, or open it to pick a different one — and change your default — on the spot.
Summary language control
Choose the language your meeting summaries are written in. Set it globally or override it per template, or leave it on auto-detect to follow the conversation.
Default settings for file transcriptions
A new gear on the Transcribe page sets your defaults for every file you transcribe: model, language, timestamps, and automatic export when each file finishes.
Merge speaker segments
A new setting collapses back-to-back segments from the same speaker into a single block, so diarized transcripts read like a conversation instead of a stack of fragments.
Pick realtime or batch per provider
Choose between gpt-realtime streaming and gpt-4o-transcribe batch transcription for OpenAI, and fine-tune ElevenLabs with new verbatim and audio-event-tagging options.
Auto-translate from the tray (Pro)
Flip translate-to-English on or off straight from the tray menu, without opening Settings.
Improved
Long recordings on OpenAI — Dictations and files longer than OpenAI's 25-minute limit are now chunked automatically, so long recordings transcribe cleanly instead of erroring out.
Cooler, lighter long meetings — Meeting recordings now throttle hidden animations and cap the discarded screen-capture stream, cutting CPU and GPU load substantially over long sessions.
Sync that deletes exactly what you deleted (Pro) — A restructured sync engine tracks deletions explicitly instead of inferring them, keeps every note in its own file for cleaner merges, and now syncs your expansion fill-in variables too.
Consistent exports everywhere — The notes and transcription list pages now offer the same export options as the detail pages, including SubRip and WebVTT subtitles in bulk exports.
Settings search shows the real thing — Searching Settings now renders the actual settings sections filtered to matching rows, so you can flip a switch right from the search results.
Modern British spellings — UK English conversion no longer produces archaic spellings like "instal".
Clearer no-speech errors — When a recording contains no detectable speech, Vowen now says exactly that instead of surfacing a generic transcription error.
Refreshed AI model lineup — Updated the available AI enhancement models to the latest provider releases, and retired Straico following its shutdown.
Polished notch indicator — Refined the notch indicator's styling and stopped it from getting in the way of command-mode banners. (macOS)
Fixed
Hotkeys on international keyboards: the extra key on ISO layouts (like § or º next to left Shift) can now be bound, along with better handling of other non-QWERTY layout keys.
The accent popup and emoji picker could stop working system-wide while Vowen sat idle in the background. (macOS)
The filler-word filter no longer strips "um" from German dictations, where it is a real word, and now catches "ähm" correctly.
ElevenLabs realtime transcription could drop the last word or two of a dictation.
Trailing-silence removal could occasionally clip softly-spoken final words before transcription.
Local Whisper transcriptions occasionally inserted stray spaces in the middle of long words.
Connection failures on networks with broken IPv6 routing — Vowen now falls back to IPv4.
Holding Option while selecting a screen region for command mode no longer switches focus away from the app you were working in. (macOS)
Meeting-note screenshots now capture the display you are actually working on, instead of always grabbing the primary monitor.
Restored the missing logos on connector cards.
Update from within Vowen (Settings → General → Check for updates), or download the latest build at vowen.ai.
July 11th, 2026
v0.4.10 brings a command palette, full localization into 18 languages, smarter text expansions, major Windows upgrades, and a long list of reliability fixes driven directly by your reports. Thank you to everyone who filed them, many items below link straight back to your feedback.
New
Command Palette
Press Cmd+K (Ctrl+K on Windows) to jump to any page, setting, or action in Vowen from one quick launcher. If you know what you want, you no longer need to know where it lives.
Vowen in 18 Languages
The entire interface is now localized: Spanish, French, German, Portuguese, Italian, Japanese, Korean, Chinese (Simplified & Traditional), Russian, Ukrainian, Polish, Czech, Swedish, Turkish, Vietnamese, Bulgarian, and English. You can pick your language during onboarding or change it anytime in settings.
Fill-In Fields in Expansions
Add {{placeholders}} to any expansion and Vowen pops up a quick form to complete them as the expansion fires. Placeholders support free text and dropdown options, and a new variable library (gear icon on the Expansions page) lets you define values once and reuse them across expansions.
Hold or Tap — Per-Shortcut Recording Modes
Each recording shortcut can now work as hold-to-talk or tap-to-toggle, configured individually right where you bind the shortcut.
Speaker Diarization on Windows (Pro)
Meeting notes and file transcriptions on Windows can now label who said what, powered by on-device speaker detection — the same capability Mac users already had.
Configurable Cancel Shortcut
The key that cancels a recording (Esc by default) is now a real, rebindable shortcut. Map it to anything, or disable it entirely if Esc conflicts with your editor.
Meeting Notes from the Tray
Start, pause, resume, and stop meeting notes straight from the tray menu — no need to open the main window.
Keep Obsidian in Sync (Pro)
A new "Keep notes synced" option re-syncs a note to your Obsidian vault whenever you edit it, so the vault copy never goes stale.
"Navigate To" in Workflows
A new built-in workflow step opens any website by voice. Workflow URLs also no longer require the https:// prefix — Vowen adds it for you.
Resource-Efficient Mode for Parakeet (Windows)
An optional mode keeps Parakeet fully unloaded until you record, trading a little startup speed for lower idle memory use on modest machines.
Improved
Much faster Parakeet on Windows — Parakeet now runs as a warm background service, so transcription starts instantly instead of reloading the model on every dictation.
Quick thread dictations skip the AI step — saying just a thread trigger (or a trigger plus a few words) pastes your snippet directly, with no AI-enhancement round-trip.
Connector logins, rebuilt (Pro) — connecting external tools now completes the whole OAuth sign-in inside Vowen, with tokens stored encrypted.
Completion sound for file transcriptions — switch away while a long file processes; Vowen tells you when it's done.
Easier dictionary & thread management — a quick-entry field for dictionary words, plus new import buttons for both dictionary words and threads.
Polished tags, filters & settings — smoother tag picking, a clear-filters button, scroll positions that survive navigation, and refreshed meeting-notes settings and permissions screens.
Meeting pill hidden from screen shares — the recording indicator is excluded from screen capture, so it never appears in shares or screenshots.
Silent recordings are kept, not lost — recordings over a minute that turn out silent are saved to history with a retry option instead of being discarded.
Fixed
Long dictations that decoded to empty text under heavy load are now retried automatically instead of silently producing nothing.
Dictation no longer dies mid-recording after a mic or input-source change — a watchdog detects the stall and rebuilds the stream on the spot. (macOS)
Recordings no longer get stuck on "listening" when macOS disables and Vowen restores its keyboard listener — in-flight recordings are finalized and transcribed. (macOS)
The meeting-notes pill no longer vanishes, drifts off-screen, or ignores button clicks. (Windows)
Meeting notes now capture computer audio from every active output — including virtual audio devices — instead of only the default speaker. (Windows)
Choosing a specific microphone now reliably records from that device instead of quietly falling back to the system default. (Windows)
Custom APIs serving local thinking models (like Qwen3) no longer fail the connection test while the model is still reasoning.
Clicking "Start taking notes" on the meeting banner works even when the settings window has been closed.
The hide-dock-icon setting is respected when Vowen starts at login. (macOS)
Regenerating a meeting summary no longer overwrites a title you edited by hand.
Small local models replying with an empty message alongside tool calls no longer paste raw JSON in command mode.
Changing the transcription language for meeting notes now applies correctly to the next recording.
How to update: Vowen will prompt you with the in-app update banner, or download the latest from vowen.ai.
As always — if anything feels off after updating, post it here and we'll jump on it.
June 30th, 2026
A new on-device language, a redesigned recording indicator, sturdier recordings and downloads, and a round of Windows + workflow upgrades. Update from inside the app or download the latest at vowen.ai.
✨ New
On-device Russian with GigaAM (macOS) — A new GigaAM model brings fast, private Russian transcription that runs entirely on your Mac. No internet and no API key required.
Notch recording indicator (macOS) — A sleek recording indicator that fans out from the menu bar while you dictate. Now available on every Mac.
Re-transcribe a finished recording — Re-run any completed dictation through your current model straight from its history entry. Handy after switching models or updating your vocabulary.
Stop hands-free with a tap of Fn (macOS) — When your transcribe hotkey is Fn, a single tap of the Fn key now stops an active hands-free recording — no need to reach for the full combo.
Custom scripts in Workflows (Pro · Windows) — Run your own PowerShell, cmd, or batch scripts from a workflow on Windows, just like custom scripts already work on macOS.
German interface — Vowen's interface is now available in German. Pick Deutsch from language settings.
🚀 Improved
Resilient model downloads — Large model downloads now resume and reconnect automatically after a dropped connection, so a flaky network no longer means starting over.
Cleaner endings on transcripts — Vowen now trims trailing silence before transcribing, cutting down on the stray made-up words some models add at the end of a clip.
Your full vocabulary, every time — Removed the old 50-word limit on custom vocabulary. Your entire dictionary is now passed to transcription, no matter how long it gets.
Meeting-note templates sync (Pro) — Your custom meeting-note templates now sync across your devices alongside the rest of your settings.
Tags in webhook payloads (Pro) — Webhook deliveries now include the tags on a note or transcription, so your automations can branch and route on them.
Microsoft Store apps in Workflows (Windows) — App-specific workflows can now target Microsoft Store and UWP apps, not just traditional desktop programs.
Double-click Home for Overview — Double-click Home in the sidebar to jump straight to your Overview, while a single click still keeps whatever tab you had open.
🛠️ Fixed
Silent or stalled recordings (macOS) — Fixed a case where the recorder could start but capture no audio with a frozen level bar until you restarted the app. Vowen now detects a dead audio stream on the first frame and rebuilds it automatically.
Fn hotkeys no longer leak keystrokes (macOS) — When a hotkey uses the Fn modifier, the other key in the combo is no longer also sent to whatever app you're typing in.
Special-character hotkeys across layouts — Fixed binding and matching hotkeys that use special characters (like
/ , . ; ' [ ] - =) across different keyboard layouts.Speaker names in Obsidian & webhooks (Pro) — Speaker labels are now properly resolved in notes pushed to Obsidian and in webhook payloads, instead of showing generic placeholders.
Parakeet streaming on Windows (Windows) — Fixed how voice-activity-detection parameters were passed for Parakeet real-time streaming.
June 26th, 2026
Better meeting notes, a richer editor, faster and more reliable recording, and a major reliability pass on Windows.
✨ New
System audio for meeting notes (Windows) — Meeting notes now capture the other side of the call directly from your system audio, natively. No virtual audio device and no extra setup. If the native path is ever unavailable, Vowen falls back to screen-share audio automatically.
My Notes tab — The context you type while a meeting records now has its own tab on the finished note. Read and edit your own notes after the fact, then regenerate the summary straight from them.
Slash commands in the editor — Type
/anywhere in a note summary to insert headings, lists, quotes, and more from a quick block menu.Images in note summaries — Embed images by URL, file picker, drag-and-drop, or paste. Local images are copied alongside the note so they always render.
Batch file transcription — Queue several audio or video files and transcribe them all in one pass.
Multi-select across transcriptions & history — Select multiple items and act on them together — bulk export or delete in a single action.
Bulk export of selected items — Export a chosen set of notes and transcriptions at once as Markdown, plain text, or PDF, bundled into one archive.
Subtitle export — Export any timed transcript as SubRip (
.srt) or WebVTT (.vtt).Editable transcription titles — Rename any manual transcription to keep your list organized.
⚡ Improved
Faster, more reliable recording — Warm starts, device caching, and a low-latency capture buffer cut the lag before your first word, and very short clips are padded so quick phrases like "commit" are no longer dropped.
Crash recovery on Windows — Vowen now detects and recovers from renderer and GPU-surface crashes — including a blank window or dead hotkeys after waking from sleep — restoring the app and your keyboard shortcuts without a manual restart.
Redesigned language selection — A cleaner, faster picker for your dictation languages.
Refreshed settings & memory pages — A polished pass for a more consistent, less cluttered layout.
Parallel import of meeting notes — Importing several notes at once now processes them in parallel, so large imports finish much faster.
Default models shown in notes settings — Meeting-notes settings now surface the default models you have configured.
Snappier recording indicator — Reduced transition time so it appears and updates more instantly.
Consistent transcription page — The transcription page now matches the notes page styling.
🐛 Fixed
Last word no longer cut off — Vowen drains the in-flight audio buffer after you stop, so the final word of a dictation is captured instead of clipped.
Deepgram, Mistral & xAI — Resolved several transcription bugs across these providers.
OpenRouter JSON responses — JSON object responses are now preserved when routing AI calls through OpenRouter.
Real-time preview overlap — Live previews are now scoped to their recording session, so separate recordings no longer bleed into each other.
Meeting-notes indicator drag — Fixed the drag handler so the indicator moves smoothly and stays where you drop it.
Import notes drag & drop — Dropped files are now picked up reliably.
Recording indicator position preserved — The indicator keeps its position when a banner is dismissed.
Meeting-detected banner respects its setting — It no longer appears when the prompt is turned off.
Short clips on Parakeet — Very short or empty recordings are discarded cleanly instead of surfacing a transcription error.
Platforms: macOS + Windows Pricing: One-time $49, lifetime updates Update from inside the app or download at vowen.ai.
June 16th, 2026
A packed release: Vowen now wraps up your meeting notes automatically when a call ends, keeps your devices in sync in the background, adds a new transcription model, and brings tags, smarter expansions, and sharper visuals across the board.
✨ New
Auto-stop meeting notes when the meeting ends (Pro · macOS) — Vowen detects when your meeting app releases the mic and offers to finish your notes, with a 15-second grace period and a one-click cancel.
Region capture for command mode (Pro) — Drag to select any region of your screen and pass it to command mode as visual context.
Expansion suggestions dropdown (Pro) — Start typing a
:shortcut and a live dropdown of matching expansions appears. Click one to insert it.Tag your expansions — Organize expansions with tags and filter the list by tag.
Tag manual transcriptions — Apply tags to files you transcribe manually and filter by them.
Filter meeting notes by person — Attendees now appear on each note card, and you can filter your notes by who attended.
Filter history by voice vs command mode — Show only dictations or only command-mode results.
Background auto-sync (Pro) — Vowen now keeps your notes, transcripts, and settings in sync across devices automatically — on launch, on window focus, and moments after you make an edit, with no manual sync needed.
Cartesia Ink 2 transcription — Cartesia's Ink 2 is now available as a cloud transcription model for dictation, meeting notes, and file transcription. English-only for now.
Mention dates when importing notes — Reference a date during import and notes are filed under the right day.
Per-app workflow folders — Point a workflow at a specific folder for each app.
Sync to Obsidian button (Pro) — Push a meeting note straight into your Obsidian vault in one click.
Connectors (Pro · Experimental) — Early support for connecting Vowen to Linear, Notion, Vercel, GitHub, and your Mac's own apps so command mode can act on your behalf. Opt in under Settings → Experimental.
⚡ Improved
More reliable cross-device sync (Pro) — A rebuilt sync engine merges concurrent edits from multiple devices cleanly, with smarter conflict resolution and atomic writes, so changes no longer overwrite each other.
Faster meeting notes with on-demand Parakeet (macOS) — When Parakeet isn't your default model, Vowen spins up a lightweight on-demand Parakeet to process meeting notes, so they finish quickly without keeping a model running in the background.
Rich text by default for expansions — New expansions support bold, italic, and links out of the box.
Sharper recording indicator across displays — Adapts to different resolutions and DPI scaling, staying crisp when you move between monitors.
Refined meeting-notes recording indicator — A cleaner, more polished look.
Smoother audio waveforms — Waveform rendering moved to the main process for faster, lighter playback, even on long recordings.
Full-length diarization with Mistral — The latest Mistral model lifts the audio-length cap, so speaker diarization runs on complete recordings without chunking.
Clear errors if a model fails to download — Onboarding now surfaces a clear message instead of silently stalling.
Queued mute/unmute events — Rapid toggles now land reliably and in order.
🐛 Fixed
Cleaner shutdown on force quit — Fixed a crash that could occur on force-quit and ensured resources are released properly.
Meeting-end detection during dictation (macOS) — Detection now pauses while you dictate or run a command, so it won't cut notes short.
Tray icon shows all configured models — The tray menu now lists every model you've set up.
Indicator no longer steals focus at the top — Fixed the indicator's click area pulling focus when positioned at the top of the screen.
More reliable active-app detection on Windows — Improved detection and fixed cache invalidation so focus is no longer stolen.
Native text writer: short phrases & new lines (macOS) — Fixed dropped short phrases and mishandled new lines.
Mistral dropping the last few words — Streaming Mistral transcriptions now get a longer grace period to finalize, so the end of what you said is no longer cut off.
Update from inside the app or download the latest at vowen.ai.
June 7th, 2026
New
Screenshots as meeting context — attach screenshots so the AI can read your screen for better summaries (macOS + Windows)
Rich-text threads — bold, italic, and links, with plain text, markdown, and HTML output
Idle pill — an optional minimized bar at the screen edge; hover to expand and record
Paste last dictated text — a shortcut to re-paste your most recent dictation anywhere
Search threads, dictionary & expansions — filter entries with built-in search
Speaker label suggestions — autocomplete speaker names from ones you've used before
Copy part of a command-mode result — select and copy just a sub-section
Optional timestamps — turn off per-segment timestamps when transcribing a file
Improved
Streamlined export options for notes and transcriptions in one cleaner modal
Custom expansions no longer limited by the built-in ones
Cleaner date separators in the notes list
Refreshed Cerebras model lineup
More accurate names in AI enhancement
Pick which OneDrive account to sync with (Pro)
Fixed
OpenAI temperature issue when connecting through OpenRouter
Webhooks now send an
application/jsoncontent-typeTranscription error states now clear at the right time
Stuck modifier keys after system resume
More reliable local Whisper server recovery
Local Whisper crashing on the latest NVIDIA GPUs (Blackwell / RTX 50-series)
Parakeet & Whisper failing to run on pre-2012 CPUs
May 29th, 2026
A big release packed with new features, faster command mode, more reliable streaming, and a long list of fixes.
New
Search Across Transcripts — Find anything you've ever dictated. Full-text search across every past transcription, with quick jump-to-result.
Audio Playback & Scrub Controls — Play back transcription audio with proper scrubbing controls — pause, seek, and re-listen to any segment.
Ask Questions Live During Meetings (Pro) — Ask Vowen anything mid-meeting and get answers in real time, without ever leaving the call.
Follow-Up Questions in Command Mode — Refine a command-mode response with follow-up questions instead of starting over.
Speaker Diarization with Groq (Pro · macOS) — Groq Whisper transcriptions now support Pyannote-powered speaker diarization.
Gemini Speech Models — Google's Gemini speech models are now available as a cloud transcription option.
OpenAI Real-Time Streaming — OpenAI is now supported as a real-time streaming transcription provider.
Group Notes by Tags — Organize meeting notes by tag with a dedicated filter bar and default filtering options.
Webhook Delivery Logs (Pro) — Track every webhook fire — see status, response, and payload for each delivery from settings.
Merge Speaker Labels (Pro) — Collapse multiple speaker labels into one across a transcript with a single action.
Add Context Mid-Meeting — Type quick context notes directly into the meeting-notes recording indicator while recording.
Cancel Follow-Ups Midway — Stop a running follow-up question mid-flight instead of waiting for it to finish.
Hide the Recording Indicator — A new setting lets you suppress the on-screen recording indicator entirely when you don't want it visible.
App-Native Timer — The in-app timer is now a true native window with smoother visuals and better behavior across spaces.
Improved
More Reliable Parakeet Streaming with VAD — Voice activity detection now drives Parakeet streaming for cleaner segments and more reliable real-time transcription.
Auto-Switch Models on Failure — Command mode and custom utilities now seamlessly fall back to another model when one fails or hits a rate limit.
Much Lower Command-Mode Token Usage — Default command-mode calls now use under 1.5k tokens (down from 8k) — faster, cheaper, and less rate-limit pressure.
Meeting Notes Settings, Reorganized — Meeting note settings now live as a dedicated tab inside the main Settings modal, with a cleaner layout.
Pausing Notes Pauses Everything — Pausing a meeting note now pauses the recording indicator and timer too, so the UI stays in sync with the recording.
Halo on the Recording Indicator — A subtle halo around the recording indicator makes it easier to see at a glance when Vowen is live.
Empty State on Summaries — A friendlier empty state appears when there's nothing to summarize, instead of a blank panel.
Finer Transcript Segment Controls — More precise controls for merging and splitting individual segments inside a transcript.
Faster Mic Unmute After Recording — Your mic unmutes the instant recording stops, instead of waiting for transcription processing to finish.
Auto-Translate for Parakeet (Pro) — Auto-translate-to-English now works with on-device Parakeet transcriptions.
Hide Live Ask When Real-Time Is Off — The live-ask UI now stays out of sight unless real-time transcription is actually enabled.
Smarter Command-Mode Banner — Better formatting in the command-mode banner, plus improved link-opening behavior.
Obsidian Sync Improvements (Pro) — Notes synced to Obsidian now go into the right vault folder and include transcript and template name as parameters.
Updated DeepSeek Models — Refreshed the available DeepSeek model lineup with the latest releases.
Parakeet Chunking on Windows (Windows) — Parakeet now chunks longer audio on Windows for more reliable transcription of long recordings.
SwiftShader Fallback on Windows (Windows) — Vowen now falls back to SwiftShader when GPU rendering isn't available on Windows, instead of failing to launch.
Cleaner Notes Settings Modal — The notes settings modal has been simplified and decluttered.
Fixed
Esc & Tab Crash on Global Shortcuts — Fixed a SIGTRAP crash that could occur when Esc or Tab were involved in globally registered shortcuts.
Groq Transcription Timestamps — Fixed an issue with timestamps in Groq transcriptions.
Parakeet Streaming Overlap — Fixed an overlapping live-streaming bug with Parakeet that could duplicate or fragment segments.
Live Transcription Time Segments — Fixed timing of live transcription segments and the auto-scroll behavior that follows them.
Slack Webhook POST Formatting — Fixed broken Slack webhook payloads when delivered via POST.
External Speaker Source Muting — Fixed an issue where external speaker sources weren't being muted reliably before recording.
Banner Cut-Off on Resize — Added a ResizeObserver so the recording / command-mode banner no longer gets clipped when its container resizes.
Follow-Up Banner on Empty Speech — The follow-up banner no longer dismisses itself when a follow-up turns out to be an empty speech segment.
Card Colors in Dark Mode — Card backgrounds are now consistent across dark mode throughout the app.
Google Workflow Prefix — Fixed an incorrect prefix used when firing Google Workflow integrations.
Retry Success for Custom Utilities — Command mode now shows success correctly when a file-based custom utility succeeds on retry.
Self-Triggered Hotkeys (macOS) — The app's own simulated Cmd+C / Cmd+V key events no longer get mistaken for real user releases and cancel an active recording.
Meeting Detection Cleanup on Quit (macOS) — Meeting detection now stops cleanly when Vowen quits, instead of lingering in the background.