MacWhisper Release Notes

New

• Languages: MacWhisper is now available in Spanish, French, Japanese, Simplified Chinese, Swedish, and Finnish.
• Meetings: Enable Automatically Stop Recording to stop recording 10 seconds after a meeting ends, or dismiss the alert to keep recording.

Improvements

• Translation feedback: Submit translation feedback from the Help menu in every supported app language.

Bugfixes

• Fixed: Dictation dictionary entries now retain spaces, punctuation, numbers, and capitalization.
• Fixed: On-screen context no longer joins separate words together during dictation.
• Fixed: Qwen3-ASR transcription progress now updates correctly.

Improvements

• Recording: smoother waveform rendering and reduced processing overhead.

Bugfixes

• Dragging recordings from apps such as Voice Memos could get stuck, including in Batch and Podcast mode.
• Dropping a file onto the transcript editor could replace the displayed transcript with the file’s contents.
• Obsidian exports could fail when note titles contained slashes, colons, or other unsupported characters.
• Fixed a layout-related crash on macOS 27.
• Fixed the Roadmap layout and Manage Export Formats button styling in Settings.

New

• Folders: Organize your transcriptions into folders and subfolders, with drag and drop, keyboard navigation, and a sidebar layout that remembers which folders are expanded.
• Live meetings (Beta): Transcribe meetings as they happen with speaker identification. Enable this in Advanced Settings → Recording Settings with a supported model such as Parakeet or WhisperKit. Requires Pro.
• Sharing: Send audio directly to MacWhisper from other apps using the macOS Share menu, including Voice Memos.
• Shortcuts: On macOS 27, transcribe audio or video with your choice of model, language, speaker identification, and whether to save the result to your library.
• Spotlight and Siri: Find and open transcriptions through Spotlight and Siri on macOS 27, with searchable transcript content and support for referring to the transcription currently on screen.
• Spotlight and Shortcuts: Find transcriptions by their contents and open, retrieve, or share them through Siri and Shortcuts on macOS 27.
• Shortcuts export: On macOS 27, retrieve transcript text and pass transcriptions between actions for saving, sharing, previewing, and formatted export.
• Integrations: Send AI summaries to your connected services, including formatted headings and lists in Notion.
• Dictionary: Add multiple dictionary entries at once by pasting a list.
• AI models: Added GPT-5.6 Sol, Terra and Luna, GPT-6 Astra, and Claude Fable 5.1.

Improvements

• Transcript editor: Refined the layout and added options to show milliseconds or hide timestamps.
• Timecodes: Automatically detect embedded start timecodes in supported MOV and MP4 files and respect them in the transcript editor.
• Drag and drop: Drag transcriptions into Finder to export a .whisper file, or into text destinations to insert the transcript.
• Search: Find transcriptions by their original filenames and search for exact phrases using quotation marks.
• Imports: Improved handling of mixed imports containing media, transcripts, and models, with clearer reporting when something fails.
• Accessibility: Improved VoiceOver support and translations throughout the app.

Bugfixes

• Fixed: Failed retranscriptions could replace the original transcription. Originals are now preserved until retranscription completes successfully.
• Fixed: Retranscribing completed live meetings could fail to find the recorded audio.
• Fixed: Permanently deleting voice memos and dictations could leave associated audio files behind.
• Fixed: Deleted transcriptions could still appear in dictation history or affect sidebar counts.
• Fixed: Transcription queues could get stuck after cancelling work or encountering an error.
• Fixed: Copying or exporting transcripts without speaker labels could lose paragraph breaks.
• Fixed: Renaming folders from the context menu could fail to start editing.
• Fixed: Opening shared files and reopening the main window could behave unreliably.
• Compatibility: MacWhisper 15.0 requires macOS 15 or later. Users on macOS 14.x can continue using the versions up to 14.8.1 which can be downloaded from your Gumroad library.

New

• Dictation: You can now export the audio recording of a dictation from its right-click menu in History.

Improvements

• Model downloads: Models are now prepared right after downloading, so your first transcription with a new model is no longer held up by a one-off preparation step.
• Notifications: Transcription failure alerts and notifications now name the engine that failed.
• Model lists: Fetched far less often, which cuts network traffic at launch and speeds up cold starts on a poor connection.

Bugfixes

• Fixed: MacWhisper now tells you when macOS refuses access to the login keychain.
• Fixed: Deleting an AI service now also removes its stored API key from the keychain.
• Fixed: Dictation could get stuck processing and refuse new dictations if you stopped or cancelled it while the model was still loading.
• Fixed: A crash when an audio conversion was cancelled while it was still reading the file.
• Fixed: Custom AI services no longer fail when the provider returns a non-streaming response, and rejected requests now show a clearer error.
• Fixed: Groq services that used a retired chat model now migrate to a current one automatically, instead of failing every request with "Selected AI Service Not Available".
• Fixed: A flaky network could produce a wrong model list with no error shown; MacWhisper now falls back to the last known-good list.
• Fixed: Cancelling a URL download no longer tears down the progress display of a newer download started in the same field.
• Fixed: The floating playback bar no longer covers the end of the transcript in the editor.

New

• Cloud transcription: Added Cohere Transcribe and Speechmatics, including model, language, and region options.
• Deepgram privacy: Added an option to opt out of Deepgram’s Model Improvement Program; it is enabled by default.

Improvements

• AI models: Updated Google Gemini and xAI Grok models, with automatic migration from retired model selections.
• Export options: Added speaker-name, timestamp, and millisecond controls to batch exports, watched-folder presets, custom presets, and the export sidebar.
• Cloud transcription: Improved reliability, language handling, and error messages across providers.
• Provider setup: Added dedicated icons for Cohere, Speechmatics, Corti, Cartesia, Avalon, and Volcengine.
• Queue: Failed items now show clearer errors without misleading progress.

Bugfixes

• Fixed: YouTube downloads no longer fail with empty file errors.
• Fixed: Watched folders now ignore unsupported file types.
• Fixed: Transcript exports no longer show unsupported timestamps, drop lines, or add stray spacing in word-grouped output.
• Fixed: Speaker names in word-grouped exports now appear once per speaking turn.
• Fixed: Empty transcript segments could appear in OpenAI, Deepgram, and Gladia results.
• Fixed: ElevenLabs used the wrong language code for Tagalog.
• Fixed: Exported HTML transcripts now use the correct text color.

New

• Dictation can now follow your active keyboard language - turn on "Match Keyboard Language" in Settings → Advanced → Dictation Settings

Improvements

• Advanced Settings is now split into sub-pages instead of one long list
• Gemini models now show friendly names instead of raw API identifiers
• ElevenLabs transcriptions now always use Scribe v2 - Scribe v1 has been retired, and any saved Scribe v1 selection switches over automatically
• Meeting detection uses far less CPU
• Model lists no longer re-download from Hugging Face on every network change
• Refreshed the Pro tab in Settings

Bugfixes

• Fixed: The transcript inspector sidebar is shown again by default
• Fixed: downloaded WhisperKit models’ first load now works without a network connection
• Fixed: speaker labels from ElevenLabs and Deepgram now start at "Speaker 1" instead of "Speaker 0"
• Fixed: long AI responses no longer cut off after 10 minutes
• Fixed: license activation errors now wrap instead of being cut off
• Fixed: meeting detection no longer silently stops working if its background log stream dies
• Fixed: the "meeting detected" popover no longer stacks up duplicates
• Fixed: the speaker identification icon no longer flickers while speakers are being detected
• Fixed: a saved transcription language the selected engine no longer supports now falls back to Auto Detect
• mw models list CLI now includes the configured cloud transcription models

New

• Transcript editor: create and assign a new speaker directly from the “Assign Selection to” menu
• ElevenLabs: choose US, EU, India or Singapore data-residency endpoints for Enterprise accounts

Improvements

• Assistant transcription: broader language support
• URL transcription: more reliable YouTube and direct-media downloads, smarter stream selection and clearer error messages
• Search: AI-generated titles and short summaries are now searchable
• Transcript editor: small transcripts load faster and switching between transcripts does less background work
• History: smoother scrolling and faster day grouping
• Model loading: improved local-model stability
• Licensing: clearer guidance when entering a free-version license

Bugfixes

• Fixed: home search could display “No Results” even when matches were found
• Fixed: history screens could occasionally render an empty list
• Fixed: switching transcripts could send content, search or playback updates to the wrong editor
• Fixed: Deepgram and OpenAI region names could load from the wrong localization bundle
• Fixed: “No text available” was misaligned in history rows

New

• Added OpenAI gpt-transcribe as a cloud transcription option, with live streaming output and regional Chinese support
• Five new cloud transcription providers: Avalon (Aqua Voice), OpenRouter (Whisper Large V3), Volcengine (Doubao), Cartesia (Ink Whisper), and Corti (medical speech-to-text)
• Redesigned model picker showing your 3 most recently used models
• New settings sidebar icons and reorganized settings categories
• Custom Obsidian properties support
• Claude Opus 5 model support for AI features

Improvements

• Opening transcriptions is much faster
• Added missing German and Dutch translations
• Diarization models are now grouped under a Speaker Identification section in the model pickers
• Removed Groq's decommissioned distil-whisper-large-v3-en model

Bugfixes

• Fixed Apple Speech models that would disappear after relaunch
• Better support for DeepL rate limits when translating long transcripts
• Fixed export for free users in an edge case
• Fixes a potential crash on macOS 26.0 when starting a transcription

New

• Command line (CLI): speaker detection from the terminal - add --speakers to mw transcribe and get the transcript back grouped by speaker, with per-speaker paragraphs and labels. Drop the labels with --no-speaker-names, or fold speakers into any export format (SRT cues get speaker prefixes, JSON carries per-segment speaker IDs)
• CLI: transcribe straight to SRT, VTT, CSV, Markdown, HTML, Avid or structured JSON with mw transcribe --format - the JSON carries millisecond timestamps and word-level timings, made for feeding transcripts into scripts and AI pipelines
• CLI: pick a layout style and fine-tune it with the same levers as the Export panel - --style (transcript, subtitles or segments) plus flags for timestamps, end timestamps, milliseconds, speaker names, grouping by words, sentences or people, line wrapping, and Avid frame rates
• CLI: batch transcription - pass multiple files or whole folders to mw transcribe, add --recursive to include subfolders, and --output-dir to write one transcript per file while mirroring your folder structure. Failed files are reported and skipped, with a summary at the end
• CLI: choose the spoken language per run with --language (ISO codes, auto, or multilingual), validated against the selected model so unsupported combinations fail with a clear explanation instead of being silently ignored
• CLI: write the transcript to a file with --output, including streaming segments into the file live with --stream
• CLI: running mw on its own now gives a much nicer overview, with example commands to get you started
• Added Mistral Voxtral Mini Transcribe 2 as a cloud transcription option
• Added Markdown (.md) export for full transcripts

Improvements

• CLI: clearer error when a sandboxed caller (such as a coding agent) is blocked from connecting to MacWhisper
• Clearer error messages when a model download fails
• Improved the design of the info page in Settings and added a toggle for enabling automatic updates
• Clearer license validation errors for users without a license

Bugfixes

• CLI: fixed cancelling a transcription with Ctrl+C potentially stalling the transcription queue until the app was restarted
• CLI: fixed a disconnecting client potentially crashing MacWhisper mid-transcription
• CLI: fixed mw hanging indefinitely when the app closed the connection without responding
• CLI: fixed a cancelled transcription leaving a phantom entry in the history until the next launch
• CLI: fixed the progress indicator colliding with the first line of the transcript
• Fixed an issue where some Pro users could not use the Summary feature
• Fixed an empty rectangle window appearing on screen when meeting recording started
• Fixed the Notion integration test button color

New

• Added AssemblyAI as a cloud transcription option
• Added xAI (Grok) as a cloud transcription option
• Added Rev AI as a cloud transcription option

Improvements

• Live transcription now streams in order and groups into readable paragraphs as you speak
• The transcript inspector now opens by default and remembers whether you left it open
• Speaker and timestamp columns stay hidden until speaker identification finishes, so the transcript doesn't jump around
• Ogg files now convert natively where macOS supports it, and very long files report an error instead of crashing
• Refreshed the available Anthropic models for AI features

Bugfixes

• Fixed retranscribing a recording with a different language or model appearing to do nothing — the new transcript, language, and model now appear immediately
• Fixed the home screen sometimes showing "No transcription available" for a recording that had just finished transcribing
• Fixed recordings showing content from a deleted transcript — they now correctly show as untranscribed, and search no longer matches deleted transcripts
• Fixed relative date headings like "Today" in history becoming wrong after midnight
• Fixed Ogg files not being importable on macOS 14
• Fixed a rare case where a meeting retranscription that failed to start would report success and could discard the original transcript
• Fixed text export repeating the speaker's name on every line
• Fixed the Converting/Decoding progress icon being clipped
• Fixed Select All (⌘A) not working on AZERTY and other non-QWERTY keyboard layouts

New

• Added a microphone picker to the menubar, making it easy to quickly switch your preferred microphone or open microphone settings

Improvements

• Transcriptions now start faster by loading the model while preparing the audio
• Cancelling a transcription while audio is being prepared is now much more responsive
• Long sections from the same speaker are automatically divided into more readable paragraphs
• Copying a selection containing multiple speakers now includes their names
• Improved Settings opening performance and search highlighting
• Exported diagnostic logs now include macOS crash reports to help us investigate issues
• Improved transcription loading states and progress labels
• Clarified that the Voice Activity Detection setting only applies to WhisperKit models
• License keys are now hidden in Settings for MDM-managed deployments
• Improved the position of the delete button in the transcription history

Bugfixes

• Fixed an issue where Microsoft Teams recordings could be blank due to changes in the Teams app when using CoreAudio as the audio driver
• Fixed missing spaces when pasting copied transcripts into Microsoft Word and Pages
• Fixed an issue where imported .whisper files could have unplayable audio when the original media extension was missing
• Fixed media exports sometimes using the wrong file extension
• Fixed merged meeting recordings not retaining the original media filename and extension
• Fixed microphone settings not updating when changed elsewhere in the app or system

New

• Added Gladia as a new Cloud transcription provider. You can use it with your own API key. (Pro)
• You can now easily copy your 10 most recent dictations from the menubar

Improvements

• Added the option to choose the region for Deepgram. You can choose between US and EU (thanks Daniel)
• Added the option to toggle filler_words for Deepgram
• Expanded Deepgram supported languages for Nova 3
• Improved playback when you have multiple transcriptions open
• When you open a transcript in a separate window, pressing Cmd+A will select the transcript content instead of the history list
• You can interact with an opened transcript without first having to click into the editor
• When using Cloud transcription providers, the files are no longer loaded into memory when sending them to the service

Bugfixes

• The menubar icon now remembers it's position if you changed it (thanks Raphael)
• Added a potential fix for an issue where the app could use a lot of CPU while idle. If you run into this still please let us know.
• Improved sync between audio and video scrub bars
• Fixed an issue where macOS would return an error about an active FaceTime call when trying to record a meeting in an edge case (thanks Andree)

New Editor View!

You can now (finally) edit your transcript directly in the main editor view. Dramatically improved performance, easily add new paragraphs, quickly re-assign speakers, favorite any part of the transcript you want and a lot more! The old transcript view is still shown for translations, for now. Let us know what you think and if there's anything we can improve by emailing us at [email protected]!

Improvements:

• Redesigned AI services screen in settings to be clearer and a lot nicer looking
• Updated the newest AI models for most popular AI providers
• Localisation improvements
• Show the copy button in full screen translation mode
• Add filler words toggle for Deepgram

Bugfixes:

• Prevent a Documents permission prompt on first launch

New

• Added the Claude Haiku 5.5 AI model.

Improvements

• Damaged recordings, such as some Microsoft Teams exports with a corrupted stretch, are now read past the damage in one pass instead of after several failed conversion attempts, so they start transcribing sooner.
• Whisper C++: Transcribes directly from your original file, without writing a temporary WAV copy first.
• Clearer errors: a file MacWhisper can't read now says "Could not open the audio file", a video without sound says "No audio track found", and an empty recording says "No audio to be read", instead of "Operation Stopped" or an error from the engine.
• Settings: Removed "Downmix audio to mono before transcription" and "Use Argmax Audio Pipeline" from Advanced settings. All local engines now share one audio decoder that always mixes multichannel audio evenly to mono, so neither option is needed.

Bugfixes

• Fixed a crash when a live meeting transcription stopped while the speech model was still decoding. Long live streams also finish promptly.
• Qwen3-ASR now loads on the Neural Engine on M6 Macs. An already downloaded model is patched in place.
• Fixed: Local transcription could stop before the end of some MP3 and AAC recordings, with no error. This affected variable-bitrate MP3s without a length header and raw .aac files from voice recorders.
• Fixed: WhisperKit could transcribe only part of a file, or nothing, with no error. Examples: only the first second of some screen recordings, Opus audio inside MP4 files, and files whose extension doesn't match their contents.
• Fixed: Opus recordings saved with an .mp3 extension (Plaud recorders do this) gave an empty transcript with WhisperKit and were sent to cloud providers unconverted. They are now recognised by their contents and converted like any other Ogg file.
• Fixed: Files whose first audio track is disabled, such as a muted commentary or alternate-language track, were transcribed as silence. MacWhisper now transcribes the track you hear when you play the file.
• Fixed: Ogg files with an upper-case .OGG extension failed to import on macOS 15.0 to 15.3.
• Fixed: A damaged Ogg file showed "This recording is too long to import on this version of macOS" and suggested an update that wouldn't help. It now says the file can't be opened.
• Fixed: Recordings with a damaged stretch, such as some Teams exports, failed to convert for upload to Cohere and Volcengine.
• Fixed dictation pasting your old clipboard contents, or losing them: the previous clipboard comes back as soon as the dictation is pasted, and only if nothing else has changed it since.
• Managed profiles: improved how a configuration profile's settings are applied throughout the app.