Changelog

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.

v0.4.0 — Vowen Pro

The biggest release yet. Vowen Pro launches with cross-device sync, chat with notes, automatic meeting detection, custom utilities, workflows with webhooks/scripts and a lot more, all built from feedback in this community.

New

• Cross-Device Sync (Pro) — Keep your settings, snippets, transcriptions, and notes in sync across machines via iCloud, Google Drive, Dropbox, or OneDrive.

• Chat with Notes & Transcriptions (Pro) — Ask follow-up questions on any meeting note or transcript. Vowen reads the full context so answers stay grounded.

• Bring Your Own AI Provider (Pro) — Plug in any OpenAI-compatible API for transcription, notes, tones, chat, and workflows — not just the defaults.

• Auto-Translate to English (Pro) — Speak in any language and Vowen delivers the output in clean English automatically — no extra step.

• Automatic Meeting Detection (Pro · macOS) — Vowen detects when you're in a Meet, Zoom, or Teams call and surfaces meeting controls instantly.

• Custom Utilities (Pro) — Build your own AI shortcuts — translators, summarizers, formatters — and bind them to a hotkey or command-mode trigger.

• Webhooks & Scripts in Workflows (Pro) — Fire a webhook or run a script when a transcription completes. Pipe Vowen into anything in your stack.

• Rich-Text Expansions — Expansions now support bold, italic, and links — plus multiple output formats: plain text, markdown, and HTML.

• Auto-Add Corrections to Dictionary (Pro · macOS · beta) — Vowen quietly watches the edits you make to transcripts and learns your vocabulary corrections on its own.

• File Transcription Queue (Pro) — Drop audio files into a queue and let Vowen process them in the background, with progress tracking and notifications.

• Obsidian Integration (Pro) — Export meeting notes and transcriptions directly into your Obsidian vault.

• gpt-4o-transcribe Support — OpenAI's newest transcription model is now available as a cloud option alongside Whisper and Soniox.

• UK English Dictation — Real-time American → British spelling conversion with a 1,700+ word dictionary, applied as you dictate.

• Cancel Transcriptions Mid-Flight — Abort a command-mode run or a regular transcription before it pastes.

• Switch Models From the Banner — Provider chips in the recording banner let you change models without opening Settings.

• License Key Activation — Activate Vowen Pro on up to 3 devices per license — manage your devices from Account settings.

• Works Across Any Keyboard Layout — Hotkeys and expansions now adapt to your physical keyboard — AZERTY, QWERTZ, Dvorak, and beyond.

• Revamped Onboarding Flow — A redesigned onboarding walk-through introduces new users to setup, hotkeys, and Pro features.

• Share Insights Card — Generate a shareable card highlighting your transcription stats and milestones.

• Confirmation Before Device Deactivation — Vowen now asks before deactivating a device from your Pro license.

Improved

• Smoother Meeting Notes — Notes generate in the background while you keep recording. Skeleton loaders and a tray indicator show progress.

• Faster AI Responses — AI responses now stream over SSE end-to-end instead of plain HTTP — noticeably snappier across the app.

• Parakeet Is the New Default Local Model — Faster on-device transcription, with periodic warmups so the very first run is instant.

• Redesigned Notes & Transcription Pages — Cleaner detail-page layouts for both meeting notes and transcriptions, with a more focused reading experience.

• Mute Before Recording (Pro) — Vowen briefly mutes input before recording starts so stray audio (e.g. the tail of a video) doesn't bleed into your first words.

• Microphone Connecting Indicator — A clear loading state shows when the mic is still coming online.

• Meeting Detection Survives Sleep & Power Events (macOS) — Detection automatically resumes after sleep, lid-close, or AC plug/unplug.

• Sensible Templates for Custom Utilities — Starter templates so you're not staring at a blank box when you create a new utility.

• Tones Respect Auto-Translate (Pro) — Tone profiles now honor your auto-translate-to-English setting.

• Focus Vowen On Gated Features — Clicking a Pro-gated feature now brings Vowen to the foreground so the upgrade prompt is visible.

• Faster & Cheaper AI Calls — Reduced default prompt size and enabled prompt caching — lower cost and less rate-limit pressure for AI features.

• Cleaner Obsidian Note Titles — Notes synced to Obsidian no longer prepend the date in the title.

Fixed

• Modals Closing on Drag Release — Fixed all modals (including Edit Expansion) closing when a text-selection drag ended on the overlay.

• Meeting Detection Swallowing Esc (macOS) — Fixed Esc key being captured by meeting detection instead of reaching the app.

• Custom API Toolbar — Fixed toolbar issues when using a custom OpenAI-compatible API.

• Failed Transcription Border — Fixed visual border issue on failed transcription entries in the list.

• Emojis & Serialization in Notes — Fixed emoji handling and serialization errors that could break note rendering.

• Deadlock on Power Resume — Fixed a rare deadlock that could occur when the system resumed from sleep.

• Tones on Windows (Windows) — Fixed tone profiles not applying correctly on Windows.

• HTTP Fallback on ECONNRESET — SSE streams now gracefully fall back to HTTP when the connection is reset by the server.

• Speaker Labels Missing From PDF Exports — Speaker labels now appear correctly in PDF exports.

• Expansions on Certain Keyboard Layouts (Windows) — Fixed expansions not firing on certain keyboard layouts on Windows.

• Recording Banner From Inside Vowen — Fixed the recording banner appearing when recording from within Vowen itself.

• macOS Accessibility Re-Prompt (macOS) — Vowen now re-prompts for accessibility permissions correctly after they're revoked.

• Windows SVG Asset Build (Windows) — Fixed Windows build issues affecting SVG assets.

• Silence-Detection Sensitivity Clamp — Clamped enhanced silence-detection sensitivity to a maximum of 5 to prevent overly aggressive cutoffs.

v0.4.1

A short follow-up to v0.4.0.

Fixed

• OpenAI Reasoning Effort — Reasoning effort is now correctly applied for OpenAI models that support it (o-series).

v0.4.2

Speaker diarization expands to on-device Parakeet, and notes/expansions get a proper rich-text editor.

New

• Speaker Diarization with Parakeet (Pro) — Speaker labels for transcripts and meeting notes are now available with the on-device Parakeet model, so you can diarize without sending audio to the cloud.

• Advanced WYSIWYG Rich-Text Editor — A new rich-text editor for notes and expansions with bold, italic, lists, headings, links, and more.

v0.4.3

Big release for meetings and transcripts — Speaker diarization with Whisper, audio waveforms, a real-time meeting note preview, and a long list of polish + fixes across the app.

New

• Audio Waveform on Meeting Notes — Meeting notes now show a scrubbable audio waveform. The transcript scrolls and highlights in sync as audio plays, so you can jump to any moment in the conversation by clicking the waveform.

• Real-Time Transcription Preview for Meeting Notes (Pro · experimental) — See your meeting note transcription appear live as the recording runs, so you don't have to wait for the session to end.

• Speaker Diarization with Whisper (Pro · macOS) — Whisper models can now label speakers using Pyannote, in addition to Parakeet diarization that shipped in v0.4.2.

• Parakeet Japanese & CTC-Mandarin — Two new on-device Parakeet models for Japanese and Mandarin transcription.

• Reassign Speaker Labels (Pro) — Rename and merge speakers across a meeting note or transcript with a single edit. Changes apply to the whole transcript at once.

• Double-Tap Hotkey Transitions — Trigger start/stop actions by double-tapping supported hotkeys, with new lock-in semantics for hands-free recording.

• On-Demand Webhook From Note Details (Pro) — Fire a configured webhook directly from a meeting note's detail page, no workflow trigger needed.

• Export All Notes as ZIP (Pro) — One-click bulk export of every meeting note as a single ZIP archive (audio + transcript + summary).

• Movable Meeting Notes Recording Indicator — Drag the recording indicator anywhere on screen and Vowen remembers the position across sessions.

Improved

• Custom Instructions for AI Enhancement is now free for everyone — Previously a Pro feature; now available on every tier.

• Audio Waveforms on Manual Transcriptions — The same waveform UI now applies to manual transcriptions, not just meeting notes.

• Real Speaker Names in Note Summaries — Summaries reference actual speakers instead of generic "Speaker 1" placeholders.

• Sticky Navbar on Detail Pages — Top navigation stays in view while scrolling notes and transcription detail pages.

• Expansions & Custom Utilities in Import/Export (Pro) — Your expansions and custom utilities are now included when you back up or restore Vowen data.

• More Hotkey Keys Supported — Expanded the set of keys you can bind to shortcuts and double-tap triggers (PageUp/PageDown, Home/End, and more).

• Updated AI Model Lineup — Refreshed the list of available AI enhancement models with the latest releases from OpenAI and Gemini.

Fixed

• Workflow Query Prefix — "Google Formule 1" no longer becomes "e Formule 1" in the search. A stray leading "e " is now stripped from extracted queries.

• Windows Audio Playback — Fixed audio waveform/player failing to load on Windows because of a path-encoding bug.

• Mistral Context Bias — Context bias now applies correctly to Mistral transcriptions; vocabulary terms are validated and deduped before the API call.

• Double-Tap Misfire — Fixed an edge case where double-tap could trigger unintentionally.

• Default State on Detail Pages — Meeting notes and transcription detail pages no longer load with the wrong default selections after IPC hydration races.

• Note Import Failure — Fixed an error when importing notes (especially MP3/M4A/MP4) by routing them through ffmpeg conversion.

• Recording Indicator Position — The meeting-notes recording indicator now reasserts its position more reliably across screen changes and after sleep/wake on Windows.

This update introduces Expansions — a system-wide text expander built right into Vowen — along with Tones on Windows, dynamic AI model updates, resource efficient mode for local Whisper, and several quality-of-life improvements.

New Features

• Expansions: Type a shortcut like :date or :time anywhere on your system and it instantly expands into the full text. Create your own custom expansions for emails, addresses, signatures, or anything you type often. Includes a guided tutorial to get started and built-in expansions out of the box.

• Tones on Windows: Tone profiles are now fully supported on Windows — customize how your transcriptions sound across different contexts, just like on macOS.

• Dynamic AI Models: Available AI models are now fetched from the server, so new models appear automatically without requiring an app update.

• Resource Efficient Mode: Use local Whisper models without keeping the server running in the background. The transcription server starts on demand and shuts down after, saving system resources.

Improvements

• Command Mode Confirmation: Command mode now shows a confirmation banner before pasting, letting you review, copy, or cancel the result.

• Workflow Trigger Phrases: Workflows now use trigger phrases directly instead of separate names, making them simpler to set up.

• Keyboard Hook Stability: Improved reliability of global keyboard shortcuts, including guardrails against suppressing system shortcuts and better handling of overlapping hotkeys.

• Filler Word Removal: Filler word stripping no longer removes newlines and text formatting from transcriptions.

• Custom Instructions UX: Added discard banners and a confirmation modal when clearing custom instructions, so you don't lose work accidentally.

• Built-in App Shortcuts: Built-in apps like Browser and Finder are now included in the app selection dropdown for workflows and expansions.

Fixes

• Fixed forward/back mouse button hotkeys not registering correctly

• Fixed provider logos not displaying properly in dark mode

• Fixed bottom positioning for command mode recording indicator

• Fixed enter key accidentally closing modals

Release Date: April 27th, 2026

v0.2.7 is a big one — four new provider integrations, native text selection on both macOS and Windows, undo cancellation, export support for manual transcriptions, and a long list of quality-of-life improvements.

New Features

xAI Transcription Real-time streaming and batch transcription powered by xAI Aurora. Supports full speaker diarization and 25 languages. Connect your xAI API key in Speech Models to get started.

Speechmatics Transcription Real-time and batch transcription via Speechmatics with speaker diarization and support for 50+ languages. Auto-detect is available for batch transcription; real-time requires a language to be selected.

Cerebras AI Enhancement Connect Cerebras for fast AI-powered transcription enhancement. Supports Llama 3.1 8B and Qwen 3 235B models via the official Cerebras SDK.

AWS Bedrock AI Enhancement Use AWS Bedrock foundation models for AI enhancement. Vowen dynamically discovers available models in your region — just provide a bearer token and region.

Undo Cancellation Accidentally cancelled a recording? Hit Undo within 5 seconds to resume right where you left off. Your audio buffer is preserved, so nothing is lost.

Export Manual Transcriptions Export manual transcriptions to TXT, PDF directly from the transcription detail page. Speaker labels and timestamps are preserved in exports.

Language Selection in Modals Choose the transcription language directly inside the Notes and Manual Transcribe modals. The language list updates dynamically based on the selected model.

Start Minimized to Tray (Windows) Launch Vowen straight to the system tray on startup. Access it anytime from the tray icon without it taking up space on the taskbar.

OpenAI Responses API Format Custom API servers using OpenAI's newer "responses" format are now auto-detected and fully supported alongside the standard chat completions format.

Improvements

Native Text Selection (macOS) Selected text is now read using the native Accessibility API instead of clipboard manipulation. Your clipboard is never touched during text selection, eliminating clipboard corruption.

Native Text Selection (Windows) Selected text is now read using the native UI Automation API instead of clipboard manipulation. Supports modern controls including Edge and other TextPattern2-compatible apps.

Reliable Long Text Insertion (macOS) Long transcriptions are now chunked at sentence boundaries before being inserted. A small delay between chunks prevents macOS from delivering keyboard events out of order — no more jumbled paragraphs.

Sleep Prevention During Notes (macOS) Your Mac will no longer go to sleep while a meeting notes session is in progress. The blocker is released when notes stop, and locking the screen won't interrupt your session.

Notes Summary Language Meeting note summaries are now generated in the same language as the meeting content, instead of defaulting to English. Works across segment summaries, final summaries, and full meeting notes.

Vocabulary for More Providers Custom vocabulary terms are now sent to ElevenLabs (keyterms), Mistral (contextBias), and Sarvam (prompt) for better recognition of domain-specific names and jargon.

Transcript Editor Performance Editing long transcripts is now significantly faster. Text areas are memoized and only the changed segment is resized, reducing layout thrashing during editing.

Streamlined Modals The Notes, Transcribe, and Import modals have been redesigned with portal-based dropdowns, provider sublabels, and a cleaner visual layout.

Tone Disconnection Warning When disconnecting a model that's currently used by one or more tone profiles, you'll now see a warning listing the affected tones.

Dismiss AI Error Banner AI enhancement error notifications can now be dismissed for one hour using the "Hide 1hr" button, so repeated errors don't interrupt your workflow.

Local API Servers Without Keys Custom and local API servers no longer require an API key. If you're running a local setup, just providing a base URL is enough.

Fixes

• Fixed speaker labels not getting saved when the transcript was edited at the same time

• Fixed a bug that prevented retrying a failed transcription from working correctly

• Groq transcriptions that produce repetitive hallucinated text are now automatically detected and retried

• Fixed incorrect transcription providers appearing in the Notes and Manual Transcribe modals

• Custom instructions now clearly indicate when AI Enhancement needs to be enabled first

We're excited to ship v0.2.6 with a set of highly requested features, quality-of-life improvements, and a solid round of bug fixes.

New Features

Multiple Tone Profiles (macOS) Create and manage multiple tone profiles, each with its own name, icon, AI model, transcription model, and target apps. Switch between them automatically based on the active application.

Filler Word Removal Automatically strip filler words like "um", "uh", and "like" from your transcriptions for cleaner, more polished output.

Edit Transcripts Edit your transcribed text directly after recording — fix mistakes, remove unwanted phrases, or refine the output before using it.

Import & Export Data Back up or migrate your transcripts and settings with a full import/export feature. Take your data with you.

Enhanced Silence Detection (Experimental) A new experimental silence detection algorithm provides more accurate end-of-speech detection in noisy environments.

Hide Recording Indicator Choose to hide the floating recording indicator entirely, or continue controlling whether it appears at the top or bottom of your screen.

Clipboard Image Handling Context awareness now reads images from your clipboard, letting you reference screenshots or visuals when using AI-powered commands.

Improvements

Guided Tour After First AI Connection After connecting your first AI provider, the app now walks you through key features with an interactive guided tour.

AI Connection Flow Setting up your AI provider is now handled in a focused modal — no need to navigate away from what you were doing.

Workflows Modal The workflows modal has been standardised with a consistent layout and improved visual hierarchy.

More AI Enhancement Examples The AI enhancement modal now ships with more built-in prompt examples to help you get started faster.

Whisper Banner Model Prompt The Whisper server restart banner now prompts you to download a local model if none is found, instead of silently failing.

Fixes

• Fixed pause and stop buttons not responding correctly during a recording session (Windows)

• Fixed the pinned taskbar icon not reliably opening the settings window (Windows)

• Fixed clipboard contents being corrupted during text insertion

• Fixed mode switching between transcribe and handsfree not considering alternative shortcuts

• Fixed the app unexpectedly gaining focus when the settings window was opened (macOS)

• Added a 500ms grace period when switching primary shortcuts to prevent accidental mode changes

• Keyspy and the keyboard hook now automatically restart when certain input events go missing (macOS)

• Fixed the settings window appearing at an incorrect position on screen

• Fixed other registered shortcuts firing while a meeting notes session is in progress

• Fixed an issue preventing AssemblyAI from connecting correctly as a transcription provider

Release Date: April 11th, 2026

New Features

• Custom prompt templates for meeting notes — create and manage multiple templates to control how notes are structured and generated

• Failed transcriptions can now be retried directly from the notification banner

• Custom search query configurable per workflow to control what context gets used when a workflow runs

• Parakeet local model is now pre-warmed at launch so the first transcription starts without delay (macOS)

• Improved direct text insertion using a new native binary with SendInput and Unicode support, reliable across all keyboard layouts (Windows)

• Minimize button now available in the app window (Windows)

Improvements

• Microphone RMS sensitivity increased to better detect quieter voices and softer speech

• App now shows an incomplete download state for speech models so you always know when a download is in progress

• Meeting notes shortcut now ships with a sensible default hotkey out of the box

• Screenshots captured for context awareness are now downsampled before being sent, reducing latency and token usage

Fixes

• Fixed a flickering issue in real-time transcription caused by token update callbacks not being reset between sessions

• Fixed timeout errors that occurred when audio was paused during a real-time transcription session

• Fixed direct text insertion incorrectly copying transcribed text to the clipboard as a side effect

• Fixed an issue where changing the selected microphone did not take effect until the app was restarted

• Fixed a bug where transcribed text was being written to the clipboard twice

• Cancelling a meeting notes session no longer incorrectly shows the transcription indicator

• Fixed a visual overflow issue in the notes modal that caused content to be clipped

• Fixed sound cue volume levels playing at incorrect levels (Windows)

Download & Update

Auto-update: Existing users receive automatic prompts

Manual: Visit vowen.ai for the latest version

Acknowledgment

Thanks to everyone who submitted feedback and bug report!

Release Date: April 3rd, 2026

New

• Settings have been moved into a clean overlay modal, making it faster to access and navigate without leaving your current context.

• You can now assign multiple keyboard shortcuts and individually toggle AI enhancement for hands-free and regular transcription modes.

• A dedicated keyboard shortcut is now available to instantly start a meeting notes recording.

• A new setting lets you skip saving the voice log after transcription if you prefer not to keep the audio recording.

• The app now shows a clear warning when screen recording permission is required, making initial setup smoother on macOS.

• You can now disconnect API providers such as OpenAI and AssemblyAI directly from within the app.

• Choose between paste and direct text insertion as your preferred method for inserting transcribed text into other apps (macOS only)

• Manual transcription sessions can now be cancelled while they are in progress.

Improvements

• The shortcuts configuration UI has been redesigned for a cleaner, more intuitive experience with better conflict detection.

• Command mode now shows a truncated preview of the selected text, and the executed state is surfaced clearly in the UI.

• The notes detail page UI has been simplified and the delete flow for manual transcriptions and notes has been improved.

• The app now correctly reasserts its always-on-top position when taking notes on Windows, preventing it from being hidden behind other windows.

• Toast notifications have been visually refreshed for a cleaner look.

Fixes

• Fixed a bug where shortcut conflicts were not being detected correctly, which could result in silent key binding issues.

• Fixed an issue where language hints were not being passed correctly to the Soniox transcription service.

• Fixed the pause functionality for real-time transcription sessions.

• Fixed an issue where the screen sharing state was not being tracked correctly, causing unexpected behaviour.

Download & Update

• Auto-update: If you're already running Whispr, you'll be prompted to update automatically.

• Manual download: Head to vowen.ai to download the latest version.

Thank You 🙏

Thanks to everyone who submitted feedback and bug reports — you're helping shape Whispr into a better tool. Keep it coming at hello@vowen.ai

Date: March 28th, 2026

New Features

• Edit Meeting Notes — You can now edit meeting notes directly in the detail page using a rich block editor. Type using markdown rules and it gets auto-converted as you write.

• Import Meeting Notes — Meeting notes can now be imported, making it easy to bring in recordings and notes from outside the app.

• DuckDuckGo & YouTube in Workflows — Workflows can now trigger DuckDuckGo and YouTube searches, expanding what you can automate after a transcription.

• Microphone Selection — You can now select which microphone to use in the Notes section before starting a recording.

Improvements

• Meeting Notes Memory & Chunking — Memory usage for meeting notes has been reduced and long recordings are now chunked when sent to Mistral, improving reliability for large files.

• Microphone Change Handling — The app now detects microphone changes gracefully and recovers without requiring a restart.

• Audio Flushing — Pending audio chunks are now flushed at the end of a recording for both ElevenLabs and the native recorder, preventing audio from being silently dropped.

• Notes Title Editing — The notes title now uses the same inline edit pattern as other titles, and the transcript UI has been cleaned up.

• Menu Organization — Quit has been moved above Privacy Policy in the menu, and Copy Last Transcript has been repositioned on Windows for a more consistent layout.

Fixes

• OpenAI max_completion_tokens — Fixed an issue where the wrong token limit parameter was being sent to the OpenAI API, which could cause requests to fail.

• Meeting Notes Status Toggle — Fixed a bug where meeting notes stuck in a failed state would not update to success after being regenerated.

Download & Update

• Auto-update: If you're already running Whispr, you'll be prompted to update automatically.

• Manual download: Head to vowen.ai to download the latest version.

Thank You 🙏

Thanks to everyone who submitted feedback and bug reports — you're helping shape Whispr into a better tool. Keep it coming at feedback@vowen.ai