Guides

VoiceInk vs superwhisper on a Mac: pay once for open code, or start free, and a free third option

By Ryleigh Newman · Published October 5, 2026

Pick VoiceInk if you want to pay once for an open-source app on an Apple silicon Mac, and pick superwhisper if you want a free plan that never expires or dictate on Windows and Android too. VoiceInk is a 7-day trial, then $25 once for one Mac. superwhisper is free for unlimited dictation with local Whisper models, and its Pro plan, which holds the AI features, is $8.49 a month, $84.99 a year or $249.99 once.

Both keep your voice on the Mac by default, and both can reach a cloud model if you ask them to. I built YapToText, a free, open-source dictation app that runs on the Mac, so it shows up here as a third option, and you should read that part knowing I made it. My hands make typing difficult, so I dictate every day. This page compares what VoiceInk and superwhisper publish on their own sites, docs and GitHub, read on October 3 and October 5, 2026. I have not tested either app hands-on against the other, so nothing here ranks them by accuracy.

Download for free. No account, nothing locked, macOS 14 or later on Apple silicon. Source on GitHub.

On this page: 11 sections

1. Steps
2. Side by side
3. What each one costs
   1. VoiceInk
   2. superwhisper
4. On device or in the cloud
   1. VoiceInk
   2. superwhisper
5. Models, modes and editing by voice
   1. VoiceInk
   2. superwhisper
   3. Files and history
6. Devices, Macs and languages
7. Which one should you pick
8. Where YapToText fits as a free third option
   1. Step 1: Install it and allow two permissions
   2. Step 2: Pick a mode for the file
   3. Step 3: Drop the file and take the text
9. What each one cannot do
   1. VoiceInk
   2. superwhisper
   3. YapToText
10. The short version
11. Questions

Steps

1. Install YapToText from the Mac App Store and open it.
2. In the Get set up card on the Home page, press Continue next to Microphone and Grant next to Accessibility.
3. On the Utility page, in the Transcribe a file card, pick Raw Transcription or another mode.
4. Drag an audio or video file onto the card, or click Choose File.
5. Click Copy, or Insert to type the text into the app you were last using.

Side by side

Checked October 3 and 5, 2026, on tryvoiceink.com, VoiceInk's GitHub repository and superwhisper.com: both price lists on October 5. Prices change, so confirm on each vendor's pricing page before you buy.

The row that decides most choices is the first one: superwhisper is free for as long as plain local dictation is enough, and VoiceInk is not free past a week unless you compile it. VoiceInk's own pages disagree on the macOS version, so the table gives both; check your Mac against each. The full comparison of Mac dictation apps adds Wispr Flow, MacWhisper and Apple Dictation to the same questions.

What each one costs

The two sell different things. VoiceInk sells a copy of the app by the number of Macs; superwhisper sells the AI, by time or once, for every device you own.

VoiceInk

• The trial. Download from tryvoiceink.com and start the 7-day trial during setup.
• The licenses. Solo $25 for one Mac, Personal $39 for two, Extended $49 for three, and Startup $159 for up to ten. Each is a one-time purchase with lifetime updates and a 14-day money-back guarantee.
• The key. It arrives by email after checkout, and VoiceInk's license docs say you can get it back from the Polar portal if the email goes missing.
• The free route. The source is public under the GPL v3, so you can build it with Xcode. Its README says the compiled, paid app adds automatic updates and priority support.
• Outside the license. A cloud provider you connect for transcription or cleanup bills you on its own terms.

superwhisper

• Free. Unlimited dictation with local Whisper models, which its plans page names as Fast, Nano and Standard, plus custom vocabulary, text replacements and up to two modes without AI processing. It does not expire.
• Pro. $8.49 a month, $84.99 a year, or $249.99 once, all buying the same features: AI modes, Super Mode, file transcription, cloud models, the Parakeet and Cohere Transcribe local models, unlimited modes and speaker separation.
• Trying Pro. New users get 3,000 words of Pro features first, and the app falls back to Free when they run out.
• Every device. superwhisper says one Pro license covers unlimited Macs and Windows PCs, plus your iPhone and Android phone.
• Teams. An Enterprise plan, priced by quote, adds SAML single sign-on and SCIM provisioning, and superwhisper says a HIPAA BAA is available on request.

My own arithmetic from the prices above, checked October 5, 2026, in US dollars before any tax. Confirm on each pricing page.

On paper VoiceInk is far cheaper once you pay at all, but the comparison is not quite fair either way. superwhisper Free costs nothing and may be all you need, and its Pro license also covers a Windows PC and a phone, which no VoiceInk license does. The VoiceInk pricing page works out which license mix costs least, and the superwhisper pricing page covers when lifetime pays off.

On device or in the cloud

Here the two are much alike. Both are local by default, and both keep a door to the cloud that only you can open.

VoiceInk

• By default. Its privacy policy says transcription happens on your device with local models unless you turn on optional cloud services.
• Cloud transcription. Optional, and it sends your audio to the provider you choose, with your own API key.
• AI enhancement. Sends text, not audio, to the provider you connect. Refine, its local cleanup model, keeps it on the Mac.
• Checking the claim. The source is public under the GPL v3, so anyone can read what the app sends.

superwhisper

• Free plan. superwhisper says nothing you dictate on the free plan leaves your device. Its privacy policy, last updated June 19, 2024, says audio is transcribed on your device and no recordings or transcriptions are collected.
• Pro. Adds cloud models hosted by superwhisper, Deepgram and ElevenLabs, and the option of your own API keys. Which model a mode uses decides where that mode's audio goes.
• Offline. Its local models work offline.
• Checking the claim. It does not mention published source code, so the policy is what you have to go on.

Neither app needs the network to dictate once a local model is installed. The offline dictation guide shows how to confirm that with Wi-Fi off, and the roundup of open-source dictation apps sets VoiceInk beside Handy, OpenWhispr and FluidVoice.

Models, modes and editing by voice

Both let you choose models and build modes. They package the choice differently. VoiceInk hands you the parts to wire up yourself; superwhisper sells them already wired, in Pro.

VoiceInk

• Speech models. Setup downloads Parakeet V3 by default. Its docs also list Nemotron, Whisper, Cohere, SenseVoice and Apple Speech, which needs macOS 26, plus cloud providers with your own key.
• Cleanup. Through a provider you connect, or VoiceInk Refine, a local model that needs an Apple silicon Mac with at least 16 GB of memory and does one fixed cleanup task.
• Editing a selection. Its docs say Refine cannot use selected text, so rewriting a selection needs Ollama or a cloud provider.
• Modes. They switch by app, website, a spoken trigger phrase or a shortcut. There is also an Assistant Mode for questions, and an output that passes your words to a shell command.
• Your words. Custom vocabulary, word replacements and corrections it learns.

superwhisper

• Speech models. Whisper on the free plan; Parakeet, Cohere Transcribe and cloud models on Pro. It can also translate dictation into English with a multilingual Whisper model.
• Cleanup. Its documentation marks every language model, local or cloud, as Pro. The one local language model, S1-mini, is English only and works only in the Message and Mail modes.
• Editing a selection. Super Mode, on Pro. Its guide says it handles formatting a selection, such as title case or bullet points, and does not work well for rewriting one.
• Modes. A mode sets the voice model, the AI formatting and, on Pro, what context it may read: the active app, the text you copied and the text you selected. Modes switch by app or website, a Change Mode shortcut, the menu bar or a deep link.
• Your words. Custom vocabulary and text replacements, on every plan.

Files and history

VoiceInk transcribes audio files, lets you edit a transcript in its history, exports history as CSV, and can delete history on a schedule, from right after each dictation up to 7 days. superwhisper's file transcription is Pro, runs through your active mode, and Pro adds speaker separation. If you mostly transcribe recordings, the MacWhisper vs superwhisper comparison covers that job better.

Devices, Macs and languages

This is where superwhisper pulls ahead. If you dictate on a PC or an Android phone, superwhisper is the only one of the two that goes there.

• Other devices. superwhisper runs on Windows, iPhone and Android, under one Pro license. VoiceInk has an iPhone and iPad app, free during its beta and a one-time purchase after, and its Mac licenses do not cover it.
• Intel Macs. VoiceInk's pricing page says Apple silicon only, though its install docs suggest cloud transcription on an Intel Mac because its local models do not run reliably there. superwhisper needs macOS 13.3 or later, and its FAQ points Intel Macs to its cloud models, on Pro, because its offline models only run really well on Apple silicon. The guide to dictation on an Intel Mac covers the other choices.
• Installing. VoiceInk comes from tryvoiceink.com, from Homebrew, where the cask is named voiceink, or from the source.
• Languages. superwhisper lists more than 100. VoiceInk's coverage depends on the model, and its docs say a multilingual model does not cover every language, so check the Language picker before you download one. YapToText lists 29 plus auto-detect.
• Switches and screen readers. superwhisper's accessibility page says it pastes at the cursor, so it sits next to VoiceOver and NVDA, and that some people map its shortcut to an accessibility switch or a foot pedal. VoiceInk does not say.

Which one should you pick

Decide how you want to pay, then check the machine. Pay once and read the code with VoiceInk, or start free and pay for reach with superwhisper.

• If plain local dictation is all you need, pick superwhisper Free. It costs nothing and does not expire.
• If you want AI cleanup and dislike subscriptions, pick VoiceInk. $25 once covers the app, though cleanup needs a provider you connect or a Mac with 16 GB for Refine. superwhisper's one-time option is $249.99.
• If you want to read the source, pick VoiceInk. Its code is public under the GPL v3.
• If you want Parakeet without a subscription, VoiceInk sets it up by default. In superwhisper it is a Pro model.
• If you dictate on Windows or Android, pick superwhisper.
• If you are on an Intel Mac, VoiceInk's pricing page says Apple silicon only while its install docs point Intel Macs to cloud transcription, and superwhisper points you to its cloud models on Pro.
• If you want modes that switch on a spoken trigger phrase, VoiceInk lists that; superwhisper's switching is by app, website, shortcut, menu bar or deep link.
• If you want cleanup, editing by voice and file transcription free, on one Apple silicon Mac, neither ready-built app gives you all three for nothing, and that is the gap YapToText fills.

Still torn? superwhisper Free and VoiceInk's trial cost nothing, so dictate the same paragraph into each, with a name that usually goes wrong, before the trial runs out. The VoiceInk alternative page and the superwhisper alternative page each go deeper on one side.

Where YapToText fits as a free third option

YapToText is the app I built and use all day. It is open source under the GPL-3.0 like VoiceInk, free with no end date like superwhisper Free, and it includes the cleanup, editing by voice and file transcription that the other two charge for or ask you to set up. The ready-built app is the free one, with both models already inside.

• Models included. Whisper Large v3 Turbo (Q5), 574 MB, hears you, and Phi-3.5 Mini Instruct, 2.3 GB, cleans up. Both ship in the App Store download, so there is no provider to connect before cleanup works.
• Cleanup. Auto mode and six built-in modes, Raw Transcription, Clean Up, Note, Email, Message and Code Comment. The modes guide shows what each does.
• Editing by voice. Select text in any app, tap Right Option, say the change, and tap again. That is Quick Edit, and it runs on the bundled model.
• Files. The Transcribe a file card on the Utility page turns audio or video into plain text, on the Mac.

Here is the free file route, a feature superwhisper keeps for Pro:

Step 1: Install it and allow two permissions

• You: Get YapToText from the Mac App Store and open it. In the Get set up card on the Home page, press Continue next to Microphone, then Grant next to Accessibility.
• macOS: Asks once about the microphone, then opens System Settings, Privacy & Security, Accessibility, where you switch YapToText on yourself.
• Check: The Get set up card leaves the Home page once nothing is missing.

Step 2: Pick a mode for the file

• You: On the Utility page, in the Transcribe a file card, open the mode menu and pick Raw Transcription, or a mode such as Note.
• YapToText: Uses that mode for the file. Raw Transcription keeps every word, and the other modes clean it up on the way.
• Check: The menu shows the mode you want.

Step 3: Drop the file and take the text

• You: Drag an audio or video file onto the card, or click Choose File, then click Copy, or Insert to type it into the app you were last using.
• YapToText: Transcribes it on the Mac and gives you plain text, with no speaker labels or timestamps.
• Check: The text is where you wanted it. Quit VoiceInk or superwhisper before you try live dictation, so two apps are not listening for a key at once.

The guide to transcribing an audio file covers file types and what to do when a transcript comes back wrong.

What each one cannot do

Each of the three leaves something out, and not the same thing. VoiceInk asks for money or a build, superwhisper Free leaves out the AI, and YapToText stays on one Apple silicon Mac with Whisper.

VoiceInk

• No free ready-built app. After 7 days you buy a license or build from source.
• Built for Apple silicon. Its pricing page says Apple silicon only, its install docs point Intel Macs to cloud transcription, and its pages disagree on macOS 14.4 or macOS 15.
• Local cleanup needs memory. Refine wants at least 16 GB and does one fixed task.
• No Windows or Android. Mac, plus an iPhone and iPad app in beta.

superwhisper

• No AI on the free plan. Cleanup, Super Mode, context and file transcription are Pro.
• No real rewriting of a selection. Its own guide says Super Mode does not work well for rewriting.
• No published source. Not stated.

YapToText

• One kind of computer. An Apple silicon Mac with macOS 14 or later; nothing for Intel Macs, Windows, iPhone, iPad or Android.
• Whisper only. No Parakeet, Apple Speech or cloud models.
• Fewer languages. 29 plus auto-detect, against superwhisper's more than 100.
• Fewer mode triggers. Modes switch by app, not by website or trigger phrase.
• No hand-edited history or speaker labels. You regenerate an entry instead of editing it, and a transcribed file is plain text.

The short version

• VoiceInk. Open source under the GPL v3, local by default, $25 once for one Mac after a 7-day trial, or free if you build it.
• superwhisper. Free local Whisper dictation that never expires; AI, Super Mode and files on Pro at $8.49 a month, $84.99 a year or $249.99 once, on every device you own.
• Both. Keep your voice on the Mac by default, with a cloud option you switch on yourself. Check each pricing page before you pay.
• YapToText. Free and open source, with both models inside and cleanup, editing by voice and file transcription included, on one Apple silicon Mac.

Pay once for open code, or start free and pay for reach; if you want neither bill, there is a free third option.

If a price or feature here no longer matches VoiceInk's or superwhisper's own pages, or what YapToText does on your Mac, open an issue on GitHub and I will fix it. Every one gets read.

Download for free. No account, nothing locked, macOS 14 or later on Apple silicon. Source on GitHub.

About the author. Ryleigh Newman is a developer whose hands make typing difficult and who dictates every day with YapToText, the app this site describes. Facts about other apps come from their own sites, with the date they were read. More about the project.

Related

• superwhisper vs Wispr Flow vs MacWhisper vs VoiceInk, plus a free one
• VoiceInk pricing: the trial, the one-time licenses, and what is free
• superwhisper pricing: what the free plan includes, and what Pro and lifetime add
• A free VoiceInk alternative, open source with nothing to compile
• A free superwhisper alternative with nothing behind a paywall
• superwhisper vs Wispr Flow: which one to pick on a Mac, and a free third option
• MacWhisper vs superwhisper: recordings or dictation, and a free app that does both
• superwhisper vs Spokenly on a Mac: two free local plans, and a free open-source third option

Sources

• https://tryvoiceink.com (checked 2026-10-03)
• https://tryvoiceink.com/pricing (checked 2026-10-05)
• https://tryvoiceink.com/privacy (checked 2026-10-03)
• https://tryvoiceink.com/ios (checked 2026-10-03)
• https://tryvoiceink.com/docs/installation (checked 2026-10-03)
• https://tryvoiceink.com/docs/license-management (checked 2026-10-05)
• https://tryvoiceink.com/docs/introduction (checked 2026-10-03)
• https://tryvoiceink.com/docs/voiceink-refine (checked 2026-10-03)
• https://tryvoiceink.com/docs/recommended-models (checked 2026-10-03)
• https://tryvoiceink.com/docs/local-models (checked 2026-10-05)
• https://tryvoiceink.com/docs/cloud-providers (checked 2026-10-03)
• https://tryvoiceink.com/docs/transcription-history (checked 2026-10-03)
• https://github.com/Beingpax/VoiceInk (checked 2026-10-03)
• https://superwhisper.com (checked 2026-10-03)
• https://superwhisper.com/docs/billing/plans (checked 2026-10-05)
• https://superwhisper.com/docs/get-started/transcribe-files (checked 2026-10-05)
• https://superwhisper.com/docs/models/voice (checked 2026-10-03)
• https://superwhisper.com/docs/models/language (checked 2026-10-03)
• https://superwhisper.com/docs/modes/built-in (checked 2026-10-03)
• https://superwhisper.com/docs/modes/modes (checked 2026-10-03)
• https://superwhisper.com/docs/modes/switching-modes (checked 2026-10-03)
• https://superwhisper.com/privacy (checked 2026-10-03)
• https://superwhisper.com/for-accessibility (checked 2026-10-03)
• https://superwhisper.com/download (checked 2026-10-03)
• https://github.com/ryleighnewman/YapToText (checked 2026-10-03)
• https://apps.apple.com/us/app/yaptotext/id6786382289 (checked 2026-10-03)
• https://tryvoiceink.com/docs/mode-triggers (checked 2026-10-06)
• https://tryvoiceink.com/docs/assistant-mode (checked 2026-10-06)
• https://tryvoiceink.com/docs/custom-commands (checked 2026-10-06)
• https://tryvoiceink.com/docs/transcribe-audio-files (checked 2026-10-06)
• https://superwhisper.com/for-enterprise (checked 2026-10-06)

Questions