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.