# Flit

> Flit is the local Wispr Flow alternative for Mac: the same live, formatted
> dictation, processed on the Mac instead of a server, and bought once instead
> of a monthly subscription. Hold a key, speak, and finished,
> formatted text lands at your cursor about 0.7 seconds after keyup.
> Everything runs on the Mac: no cloud, no account, no telemetry.
> $19 once at launch (standing price $49) for up to 2 Macs, 12 months of updates included, optional
> $19 renewal, permanent license. Lifetime, updates forever, $99. Teams
> per Mac from $39, 5 Macs minimum. Requires macOS 14+ and Apple silicon.
> Made by Fore Studio (https://fore.studio), trading name of Atta Ur Rehman Shah.
> 7 days free, then $19 USD once. Sold through Paddle as merchant of record.

Key facts: more than 1,600 languages, all processed locally, 30 streaming live.
The widest coverage comes from Meta’s Omnilingual model, so accuracy varies by language.
More than 60 spoken punctuation and structure commands resolved by fixed
rules, not a model. A local codebase index repairs misheard file and
file and folder names. A personal dictionary that learns only with permission.
Snippets expand from spoken triggers. Per-app style rules. Optional context
awareness reads the field and window you are replying into, locally, in
memory for one dictation, so names and tone match the thread. Since 1.5 it
also transcribes audio and video files on the Mac (text, Markdown, SRT, VTT).
It does NOT record meetings or label speakers, and it is macOS only.

Every page below has a Markdown copy at the same address with .md added,
for example https://flit.fyi/features.md or https://flit.fyi/blog/how-to-dictate-code.md. The
copy says exactly what the page says, without the page around it. The page
without .md is the one to cite.

## Core pages

- [Features](https://flit.fyi/features): everything Flit does, and the 3 things it will not do
- [Every spoken command](https://flit.fyi/commands): the complete reference, more than 60 punctuation, symbol and structure commands plus 115 spoken emoji names, with what each produces and how it spaces. The only complete public list.
- [Pricing](https://flit.fyi/pricing): $19 once at launch (standing price $49), the arithmetic against subscriptions
- [Download](https://flit.fyi/download): requirements and launch status
- [Setup guide](https://flit.fyi/setup): install, microphone and accessibility permissions, the Fn (Globe) key setting, picking your languages and the voice model Flit recommends for them (Parakeet Ultra, Voxtral Realtime, Cohere Transcribe, Qwen3-ASR, Omnilingual, Nemotron 3.5, Apple Speech or Whisper), the formatting model, activating a license, and troubleshooting
- [Flit for Windows](https://flit.fyi/windows): the Windows version is in the works, with no date yet; the waitlist hears the day it is ready
- [Privacy](https://flit.fyi/privacy): the verifiable no-network claim, plus site policy
- [Terms](https://flit.fyi/terms) and [Refunds](https://flit.fyi/refund): 30 day refund window on a first purchase
- [Post about Flit, get 50% back](https://flit.fyi/back): the cash-back rules, Personal licenses only

## Use cases

- [Flit for Developers](https://flit.fyi/use-cases/developers): Spoken code names, spelled right (Markdown: https://flit.fyi/use-cases/developers.md)
- [Flit for Writers](https://flit.fyi/use-cases/writers): First drafts at speaking speed (Markdown: https://flit.fyi/use-cases/writers.md)
- [Flit for Founders & execs](https://flit.fyi/use-cases/founders): Clear the inbox by talking (Markdown: https://flit.fyi/use-cases/founders.md)
- [Flit for Agencies](https://flit.fyi/use-cases/agencies): Client work at speaking speed (Markdown: https://flit.fyi/use-cases/agencies.md)
- [Flit for Sales](https://flit.fyi/use-cases/sales): CRM notes without the typing (Markdown: https://flit.fyi/use-cases/sales.md)
- [Flit for Support teams](https://flit.fyi/use-cases/customer-support): Canned replies, spoken (Markdown: https://flit.fyi/use-cases/customer-support.md)
- [Flit for Lawyers](https://flit.fyi/use-cases/lawyers): Privileged notes that never upload (Markdown: https://flit.fyi/use-cases/lawyers.md)
- [Flit for Therapists & clinicians](https://flit.fyi/use-cases/therapists): Session notes that never upload (Markdown: https://flit.fyi/use-cases/therapists.md)
- [Flit for Doctors & medical](https://flit.fyi/use-cases/medical): Chart notes that stay on the Mac (Markdown: https://flit.fyi/use-cases/medical.md)
- [Flit for Students](https://flit.fyi/use-cases/students): Essays at speaking speed (Markdown: https://flit.fyi/use-cases/students.md)
- [Flit for Multilingual](https://flit.fyi/use-cases/multilingual): Switch languages mid-thought (Markdown: https://flit.fyi/use-cases/multilingual.md)
- [Flit for Hands-free & RSI](https://flit.fyi/use-cases/accessibility): Write without typing at all (Markdown: https://flit.fyi/use-cases/accessibility.md)

## Comparisons

Prices checked against each competitor’s own pricing page on the date shown on each page.

- [The 19 best dictation apps for Mac](https://flit.fyi/best-dictation-app-for-mac): ranked with a best-for label per tool and honest cons, plus 17 more checked but not ranked as dictation apps
- [comparisons.json](https://flit.fyi/comparisons.json): the whole matrix as machine-readable data, every cell dated, if you would rather read data than prose
- [Flit vs Wispr Flow](https://flit.fyi/alternatives/wispr-flow): Flit keeps every word on your Mac, and you pay once. (Markdown: https://flit.fyi/alternatives/wispr-flow.md)
- [Flit vs Superwhisper](https://flit.fyi/alternatives/superwhisper): Flit types while you are still speaking, and you pay once. (Markdown: https://flit.fyi/alternatives/superwhisper.md)
- [Flit vs SpeakMac](https://flit.fyi/alternatives/speakmac): Flit speaks more than 1,600 languages and spells your project’s file names right. (Markdown: https://flit.fyi/alternatives/speakmac.md)
- [Flit vs Spokenly](https://flit.fyi/alternatives/spokenly): Flit types as you speak and writes each app in its own tone. (Markdown: https://flit.fyi/alternatives/spokenly.md)
- [Flit vs VoiceInk](https://flit.fyi/alternatives/voiceink): Flit types as you speak and spells your code names right. (Markdown: https://flit.fyi/alternatives/voiceink.md)
- [Flit vs FluidVoice](https://flit.fyi/alternatives/fluidvoice): Flit has no cloud path at all, and every command is a fixed rule. (Markdown: https://flit.fyi/alternatives/fluidvoice.md)
- [Flit vs Snaply](https://flit.fyi/alternatives/snaply): Flit covers more than 1,600 languages, with more than 60 commands resolved by rule. (Markdown: https://flit.fyi/alternatives/snaply.md)
- [Flit vs Utter](https://flit.fyi/alternatives/utter): Flit is local by design, not as a free tier, and paid for once. (Markdown: https://flit.fyi/alternatives/utter.md)
- [Flit vs Voibe](https://flit.fyi/alternatives/voibe): Flit needs no account and has no cloud setting to switch on. (Markdown: https://flit.fyi/alternatives/voibe.md)
- [Flit vs Yaps](https://flit.fyi/alternatives/yaps): Flit types as you speak, needs no account, and is paid for once. (Markdown: https://flit.fyi/alternatives/yaps.md)
- [Flit vs Typeless](https://flit.fyi/alternatives/typeless): Flit sends nothing and counts nothing, and works with no internet. (Markdown: https://flit.fyi/alternatives/typeless.md)
- [Flit vs Aqua Voice](https://flit.fyi/alternatives/aqua-voice): Flit can read the thread too, on your Mac, and never uploads it. (Markdown: https://flit.fyi/alternatives/aqua-voice.md)
- [Flit vs Willow Voice](https://flit.fyi/alternatives/willow-voice): Flit never sends your words anywhere, so there is nothing to certify. (Markdown: https://flit.fyi/alternatives/willow-voice.md)
- [Flit vs MacWhisper](https://flit.fyi/alternatives/macwhisper): Flit types at your cursor in any app, while you speak. (Markdown: https://flit.fyi/alternatives/macwhisper.md)
- [Flit vs Apple Dictation](https://flit.fyi/alternatives/apple-dictation): Flit writes finished text, not a transcript you have to tidy. (Markdown: https://flit.fyi/alternatives/apple-dictation.md)
- [Flit vs Otter.ai](https://flit.fyi/alternatives/otter-ai): Flit turns your own words into text in any app, and records nothing. (Markdown: https://flit.fyi/alternatives/otter-ai.md)
- [Flit vs AudioPen](https://flit.fyi/alternatives/audiopen): Flit puts your words at your cursor, in the app you are already using. (Markdown: https://flit.fyi/alternatives/audiopen.md)
- [Flit vs Talon Voice](https://flit.fyi/alternatives/talon): Flit writes finished prose from speech, with nothing to set up. (Markdown: https://flit.fyi/alternatives/talon.md)
- [Flit vs Whisper (do it yourself)](https://flit.fyi/alternatives/whisper-diy): Flit is the finished product: streaming, formatting and insertion that works. (Markdown: https://flit.fyi/alternatives/whisper-diy.md)
- [Flit vs Voiskey](https://flit.fyi/alternatives/voiskey): Flit needs no account and uploads nothing, and you pay once. (Markdown: https://flit.fyi/alternatives/voiskey.md)
- [Flit vs EmberType](https://flit.fyi/alternatives/embertype): Flit types as you speak and has no cloud path at all. (Markdown: https://flit.fyi/alternatives/embertype.md)
- [Flit vs DictaFlow](https://flit.fyi/alternatives/dictaflow): Flit formats on your Mac too, so nothing is sent or counted. (Markdown: https://flit.fyi/alternatives/dictaflow.md)
- [Flit vs Aside](https://flit.fyi/alternatives/aside): Flit dictates finished text in about 0.7 seconds, with no AI to set up. (Markdown: https://flit.fyi/alternatives/aside.md)
- [Flit vs Raycast](https://flit.fyi/alternatives/raycast): Flit keeps your audio on your Mac, with no 20-minute limit on a dictation. (Markdown: https://flit.fyi/alternatives/raycast.md)
- [Flit vs Talkify](https://flit.fyi/alternatives/talkify): Flit writes finished text in more than 1,600 languages, from macOS 14 up. (Markdown: https://flit.fyi/alternatives/talkify.md)
- [Flit vs Handy](https://flit.fyi/alternatives/handy): Flit types as you speak and finishes the text for you. (Markdown: https://flit.fyi/alternatives/handy.md)
- [Flit vs Muesli](https://flit.fyi/alternatives/muesli): Flit has no hosted route, and its formatting follows fixed rules. (Markdown: https://flit.fyi/alternatives/muesli.md)
- [Flit vs TypeWhisper](https://flit.fyi/alternatives/typewhisper): Flit knows your project’s file names and writes each app in its own tone. (Markdown: https://flit.fyi/alternatives/typewhisper.md)
- [Flit vs Verba](https://flit.fyi/alternatives/verba): Flit writes finished text and nothing else, with no account. (Markdown: https://flit.fyi/alternatives/verba.md)
- [Flit vs stilltype](https://flit.fyi/alternatives/stilltype): Flit is on sale today, with the price on the page. (Markdown: https://flit.fyi/alternatives/stilltype.md)
- [Flit vs Monologue](https://flit.fyi/alternatives/monologue): Flit formats on your Mac as well, so nothing is uploaded at any step. (Markdown: https://flit.fyi/alternatives/monologue.md)
- [Flit vs Alter](https://flit.fyi/alternatives/alter): Flit makes fast dictation the core product, ready the moment you install it. (Markdown: https://flit.fyi/alternatives/alter.md)
- [Flit vs Speechify](https://flit.fyi/alternatives/speechify): Flit is for writing, not reading: your words typed, nothing uploaded. (Markdown: https://flit.fyi/alternatives/speechify.md)
- [Flit vs Tyll](https://flit.fyi/alternatives/tyll): Flit is on sale today, in more than 1,600 languages, for up to 2 Macs. (Markdown: https://flit.fyi/alternatives/tyll.md)

## Guides

Quick answers, one problem each, at https://flit.fyi/guides. The fix that needs nothing installed comes
first; what Flit does about it comes second. Facts about macOS and other apps are from their
makers’ own pages.

- [How to dictate on a Mac](https://flit.fyi/how-to-dictate-on-mac): turning on Dictation in System Settings → Keyboard, the three ways to start it (the Microphone key, the Dictation shortcut, Edit → Start Dictation), saying punctuation and new lines, how to stop, and how to change the language, the microphone and the shortcut (Markdown: https://flit.fyi/how-to-dictate-on-mac.md)
- [Mac dictation not working](https://flit.fyi/mac-dictation-not-working): why the Mac’s built-in Dictation does not start, stops, or types nothing: Dictation off, Voice Control on, the wrong shortcut or microphone, the Globe key set to something else, no connection for a language that needs one, or a Screen Time or work restriction, with Apple’s fix for each (Markdown: https://flit.fyi/mac-dictation-not-working.md)
- [Globe key opens the emoji picker](https://flit.fyi/globe-key-opens-emoji-picker-mac): the "Press 🌐 key to" setting in System Settings → Keyboard, its four options (Change Input Source, Show Emoji & Symbols, Start Dictation, Do Nothing), and the shortcuts that still open the emoji picker after you change it (Markdown: https://flit.fyi/globe-key-opens-emoji-picker-mac.md)
- [Mac dictation keeps stopping](https://flit.fyi/mac-dictation-keeps-stopping): Apple’s Dictation stops automatically when it hears no speech for 30 seconds; the other causes (a key press that ends it, a lost connection, a microphone that switched) and how to dictate long passages without it cutting out (Markdown: https://flit.fyi/mac-dictation-keeps-stopping.md)
- [Mac dictation commands](https://flit.fyi/mac-dictation-commands): every command Apple lists for Dictation on a Mac (punctuation, symbols, new line and new paragraph, capitals, numerals, emoji by name), how to say them, why a command gets typed as a word, and the point where editing by voice needs Voice Control (Markdown: https://flit.fyi/mac-dictation-commands.md)
- [Voice Control vs Dictation](https://flit.fyi/voice-control-vs-dictation-mac): the difference between Dictation (types what you say, started with a key) and Voice Control (runs the whole Mac by voice, always listening), why they cannot both be on, where each is turned on and off, and which to choose (Markdown: https://flit.fyi/voice-control-vs-dictation-mac.md)
- [Mac dictation keyboard shortcut](https://flit.fyi/mac-dictation-keyboard-shortcut): where the Dictation shortcut is set (System Settings → Keyboard → Dictation → Shortcut), the Microphone key, setting a custom shortcut such as Option-Z, how the shortcut changes the Globe key setting, and what to check when the shortcut does nothing (Markdown: https://flit.fyi/mac-dictation-keyboard-shortcut.md)
- [Dictating with AirPods on a Mac](https://flit.fyi/airpods-dictation-mac): how to choose whether Mac Dictation listens through AirPods or the Mac’s own microphone (Keyboard → Dictation → Microphone source), and why music loses quality while the AirPods microphone is in use: Bluetooth switches to its two-way mode (Markdown: https://flit.fyi/airpods-dictation-mac.md)
- [Change the dictation language](https://flit.fyi/change-dictation-language-mac): adding a Dictation language in System Settings → Keyboard → Dictation → Languages, switching language while dictating (the language next to the cursor, or the Globe key), whether there is a shortcut for it, which languages macOS 27 processes on the Mac and which get automatic punctuation, why the wrong language produces nonsense, and switching with one shortcut or automatically in Flit (Markdown: https://flit.fyi/change-dictation-language-mac.md)
- [Dictate with a mouse button](https://flit.fyi/mac-dictation-mouse-button): why macOS has no setting that starts Dictation from a mouse button, the two-step route that works (a custom Dictation shortcut such as Option-Z, then that keystroke assigned to a side button in the mouse maker’s software), why the button is a toggle and not hold-to-talk, and choosing a mouse button for dictation directly in Flit (Markdown: https://flit.fyi/mac-dictation-mouse-button.md)
- [Transcribe an audio file](https://flit.fyi/transcribe-audio-file-mac): three ways to turn a recording into text on a Mac without uploading it: the transcript in Voice Memos, the open Whisper model in Terminal, and the Transcribe tab in Flit, with what each needs and what each gives back (Markdown: https://flit.fyi/transcribe-audio-file-mac.md)
- [Wispr Flow not working](https://flit.fyi/wispr-flow-not-working): why Wispr Flow stops working on a Mac (no connection or a service incident, a VPN, a lost permission, Secure Keyboard Entry, the wrong microphone, a timed-out sign-in) and the fix for each, from its own help pages (Markdown: https://flit.fyi/wispr-flow-not-working.md)
- [Does Wispr Flow work offline?](https://flit.fyi/does-wispr-flow-work-offline): Wispr Flow has no offline mode: its own privacy page says transcription always happens in the cloud. What happens to a dictation started offline, and the dictation options on a Mac that run with no connection (Markdown: https://flit.fyi/does-wispr-flow-work-offline.md)
- [Is Wispr Flow safe?](https://flit.fyi/is-wispr-flow-safe): what Wispr Flow sends to its servers according to its own privacy pages (your audio, and with Context Awareness on, text from the app you are in), the two settings that limit it, and what a local app does instead (Markdown: https://flit.fyi/is-wispr-flow-safe.md)
- [Uninstall Wispr Flow](https://flit.fyi/uninstall-wispr-flow-mac): the full removal of Wispr Flow from a Mac: quit it and its helper, delete the app, the leftover folders in ~/Library, the login item and the permissions, and cancel the subscription separately (Markdown: https://flit.fyi/uninstall-wispr-flow-mac.md)
- [Cancel Wispr Flow](https://flit.fyi/cancel-wispr-flow-subscription): how to cancel Wispr Flow depending on who bills you (its own billing page, Apple or Google Play), what happens to access and data afterwards, how refunds work, and what the free plan allows (Markdown: https://flit.fyi/cancel-wispr-flow-subscription.md)
- [Claude Code voice dictation](https://flit.fyi/dictate-to-claude-code): the three ways to speak a prompt into Claude Code: its own /voice command (hold Space, audio transcribed on Anthropic’s servers, needs a Claude.ai login), the Mac’s Dictation, or a local dictation app; plus line breaks and what Claude Code does with long pasted text (Markdown: https://flit.fyi/dictate-to-claude-code.md)
- [Cursor voice input](https://flit.fyi/dictate-to-cursor): the ways to speak a prompt into Cursor: its own voice input (the microphone in the chat box, Cmd-Shift-Space), the Mac’s Dictation, or a local dictation app; what Cursor’s pages say and do not say about plans and where audio goes; and the difference between the chat box, the editor and the terminal (Markdown: https://flit.fyi/dictate-to-cursor.md)
- [Codex voice and dictation](https://flit.fyi/dictate-to-codex): dictating a prompt into OpenAI’s Codex: the Dictate button in the ChatGPT desktop app’s composer, why the command line’s /voice is a spoken conversation and not dictation, what to use in the terminal and the IDE extension, and where the audio goes (Markdown: https://flit.fyi/dictate-to-codex.md)
- [ChatGPT dictation on a Mac](https://flit.fyi/dictate-to-chatgpt-mac): dictating a prompt in the ChatGPT desktop app for Mac: the Dictate button in the composer, how it differs from ChatGPT Voice, what OpenAI says about where dictation audio goes and how long it is kept, the Option-Space shortcut, and the two Mac apps since July 2026 (Markdown: https://flit.fyi/dictate-to-chatgpt-mac.md)
- [Superwhisper pricing](https://flit.fyi/superwhisper-pricing): what Superwhisper costs as of October 2026: the free plan and what it leaves out, Pro at $8.49 a month, $84.99 a year or $249.99 once, the 40% student and non-profit discount, the 30-day refund, why the App Store price is higher, and the cost over three years (Markdown: https://flit.fyi/superwhisper-pricing.md)
- [Wispr Flow pricing](https://flit.fyi/wispr-flow-pricing): what Wispr Flow costs as of October 2026: the free plan capped at 2,000 words a week on desktop and 1,000 on mobile, Pro at $15 a user a month or $12 billed annually, Growth at $23 or $18, Enterprise on request, the student offer of three months free then $6 a month, and the cost over three years (Markdown: https://flit.fyi/wispr-flow-pricing.md)
- [Superwhisper not working](https://flit.fyi/superwhisper-not-working): why Superwhisper on a Mac shows "No voice found", does not paste, ignores its shortcut, pastes raw text, runs slowly or will not open: the wrong microphone, a missing Accessibility or Microphone permission, a key another app owns, a cloud model with no connection, or an old macOS, with Superwhisper’s own fix for each (Markdown: https://flit.fyi/superwhisper-not-working.md)
- [Cancel Superwhisper](https://flit.fyi/cancel-superwhisper-subscription): how to cancel Superwhisper Pro depending on who bills you (its billing portal, the App Store or Google Play), what happens afterwards (Pro until the period ends, then the free plan, with your data kept), the 30-day refund, and how to delete the account (Markdown: https://flit.fyi/cancel-superwhisper-subscription.md)
- [Uninstall Superwhisper](https://flit.fyi/uninstall-superwhisper-mac): the full removal of Superwhisper from a Mac: quit it from the menu bar, delete the app, then delete the ~/superwhisper data folder that holds recordings, history, modes and vocabulary, with a backup first and the subscription cancelled separately (Markdown: https://flit.fyi/uninstall-superwhisper-mac.md)
- [Transcribe a voice memo](https://flit.fyi/transcribe-voice-memo-mac): reading, copying and searching the transcript of a recording in the Voice Memos app on a Mac (macOS 15 or later, Apple silicon, not in every region), watching it live while you record, summarizing it with Apple Intelligence, and what to do when you need subtitles or a file Voice Memos did not record (Markdown: https://flit.fyi/transcribe-voice-memo-mac.md)
- [Make subtitles from a video](https://flit.fyi/make-subtitles-video-mac): three ways to turn the speech in a video into a subtitle file on a Mac: Final Cut Pro’s Generate Captions (Apple silicon, U.S. English, iTT converted to SRT), the open Whisper model in Terminal, and Flit’s Transcribe tab, with SRT and VTT export; plus why iMovie and QuickTime Player do not make subtitles (Markdown: https://flit.fyi/make-subtitles-video-mac.md)
- [Transcribe a Zoom or Teams recording](https://flit.fyi/transcribe-zoom-teams-recording-mac): getting a transcript of a Zoom or Microsoft Teams meeting: Zoom’s audio transcript for cloud recordings (paid plans, a VTT file), why a Zoom recording saved to your Mac gets none, the Teams transcript download (.docx or .vtt, for the organizer), and transcribing the saved MP4 or M4A on the Mac afterwards (Markdown: https://flit.fyi/transcribe-zoom-teams-recording-mac.md)
- [Transcribe a phone call](https://flit.fyi/transcribe-phone-call-mac): recording a call from the Phone app or FaceTime on a Mac (macOS 26 or later) or from an iPhone, where the recording and its transcript land in Notes, which languages get a transcript, where call recording is not available, and how to transcribe a call recording in a language Apple does not cover (Markdown: https://flit.fyi/transcribe-phone-call-mac.md)

## What is new, and how to use it

One page per big release, at https://flit.fyi/changelog: what it gives and the steps to use it.

- [Flit 1.7](https://flit.fyi/changelog/1.7): Flit 1.7 puts the whole Mac dictation app in German, French, Spanish, Japanese, Chinese, Korean and four more languages, with corrections in each. (Markdown: https://flit.fyi/changelog/1.7.md)
- [Flit 1.6](https://flit.fyi/changelog/1.6): What is new in Flit 1.6: Parakeet Ultra, Voxtral Realtime, Omnilingual ASR and Parakeet Unified, which one to use for your language, and how to switch. (Markdown: https://flit.fyi/changelog/1.6.md)
- [Flit 1.5](https://flit.fyi/changelog/1.5): What is new in Flit 1.5 and how to use it: the Transcribe tab, every way to hand it a file, raw and formatted text, exports, and the flit command. (Markdown: https://flit.fyi/changelog/1.5.md)

## Blog

Written by Atta Ur Rehman Shah, who builds Flit. Each piece discloses that,
and ranks competitors for the job they are best at.

- [The 15 best Wispr Flow alternatives](https://flit.fyi/blog/best-wispr-flow-alternatives): ranked by which reason for leaving each one removes (subscription, cloud, account), with the switching checklist and the multi-year cost arithmetic, honest about when to stay
- [The best private dictation apps](https://flit.fyi/blog/best-private-dictation-apps): three levels of verification (network-off, Activity Monitor, per-app firewall), what still leaves when the audio does not, plus the ranked list
- [Dictation vs typing: what the research says](https://flit.fyi/blog/dictation-vs-typing): Stanford 3x, the 1999 IBM result that found the opposite and why, composition vs transcription speed, a self-measurement protocol
- [The 10 best Superwhisper alternatives](https://flit.fyi/blog/best-superwhisper-alternatives): ranked by the three reasons people leave it (price, batched text, paying for breadth)
- [The best dictation apps for lawyers](https://flit.fyi/blog/dictation-for-lawyers): what a confidentiality review asks, and which tools answer it. No legal advice, no compliance claims for Flit
- [The best speech-to-text for developers](https://flit.fyi/blog/speech-to-text-for-developers): verbatim terminals, project file names, deterministic casing, Electron insertion
- [How to dictate code](https://flit.fyi/blog/how-to-dictate-code): the working setup, the spoken symbol and casing commands, and the parts that honestly do not work

## Glossary

Plain definitions of dictation vocabulary, at https://flit.fyi/glossary:
- [Globe key](https://flit.fyi/glossary/globe-key): The Globe key is the key marked with a globe symbol, and usually also with fn, on Mac keyboards. Apple calls it the Fn (Function) or Globe key. It works as a modifier for shortcuts and function keys, and pressing it on its own can change the input source, open the emoji picker, or start Dictation.
- [Voice Control](https://flit.fyi/glossary/voice-control): Voice Control is an accessibility feature built into macOS that lets you operate a Mac entirely by voice. You speak commands to navigate the desktop and apps, interact with what is on the screen, and dictate and edit text, instead of using a keyboard, mouse, or trackpad.
- [Dictation commands](https://flit.fyi/glossary/dictation-commands): Dictation commands are the words and phrases you say while using Dictation on a Mac to enter punctuation, symbols, capital letters, and formatting instead of ordinary text. Saying "comma" types a comma, and saying "new paragraph" starts a new paragraph.
- [Auto-punctuation](https://flit.fyi/glossary/auto-punctuation): Auto-punctuation is a setting of Dictation on Mac that automatically inserts commas, periods, and question marks as you dictate. It works in supported languages and can be turned on or off in System Settings under Keyboard, in the Dictation section.
- [Input volume](https://flit.fyi/glossary/microphone-input-volume): Input volume is the setting on a Mac that controls how strongly sound from the selected microphone or other input device is captured. You set it with a slider in System Settings → Sound, under Input, where you also choose which input device the Mac uses.
- [Mic Mode](https://flit.fyi/glossary/mic-mode): Mic Mode is a macOS control that changes how your Mac’s microphone treats the sound around you in apps that support it. Voice Isolation filters out background sounds, Wide Spectrum includes the sounds around you, and Standard is the standard mic mode with neither applied.
- [Secure Keyboard Entry](https://flit.fyi/glossary/secure-keyboard-entry): Secure Keyboard Entry is a Terminal setting on a Mac that prevents other apps on your computer or the network from detecting and recording what you type in Terminal. It is built on a macOS mechanism called Secure Event Input, which stops keystrokes from being passed to any process that intercepts the keyboard.
- [Live Captions](https://flit.fyi/glossary/live-captions): Live Captions is a macOS accessibility feature that shows a real-time transcription of spoken audio in a window on your screen, for audio in any app and for live conversations around you. Audio is processed on the device, and the feature is available only on Mac computers with Apple silicon.
- [Enhanced Dictation](https://flit.fyi/glossary/enhanced-dictation): Enhanced Dictation was a checkbox in the Dictation pane of Keyboard preferences on older versions of macOS that downloaded speech recognition software to the Mac so you could dictate offline. Apple’s Mac User Guide describes it for macOS High Sierra 10.13 and macOS Mojave 10.14, and it is absent from the guide for macOS Catalina 10.15 and every version since.
- [Improve Siri & Dictation](https://flit.fyi/glossary/improve-siri-and-dictation): Improve Siri & Dictation is an opt-in privacy setting that lets Apple store and review a sample of the audio from your Siri and Dictation interactions to develop and improve those features. On a Mac it is under System Settings, Privacy & Security, Analytics & Improvements.
- [Apple Intelligence](https://flit.fyi/glossary/apple-intelligence): Apple Intelligence is Apple’s set of generative AI features built into macOS, including Writing Tools for rewriting, proofreading and summarizing text. It runs on Mac models with M1 or later and MacBook Neo, uses on-device models in many cases, and sends more complex requests to Apple’s Private Cloud Compute servers.
- [SpeechAnalyzer](https://flit.fyi/glossary/speechanalyzer): SpeechAnalyzer is a class in Apple’s Speech framework, introduced with macOS 26 and iOS 26, that apps use to turn spoken audio into text. It runs an analysis session with modules such as SpeechTranscriber, using speech models that are downloaded from Apple and managed by the system.
- [Dictation](https://flit.fyi/glossary/dictation): Dictation is producing written text by speaking, with the words transcribed in or near real time at the place you are writing. It differs from transcription, which converts an existing recording into text after the fact.
- [Voice typing](https://flit.fyi/glossary/voice-typing): Voice typing is another name for dictation: entering text into an application by speaking instead of using the keyboard. The term was popularized by the Voice Typing feature in Google Docs.
- [Transcription](https://flit.fyi/glossary/transcription): Transcription is converting an existing audio or video recording into text after the fact. It is the after-the-fact counterpart to dictation, which produces text live as you speak.
- [Push-to-talk](https://flit.fyi/glossary/push-to-talk): Push-to-talk is an activation style where recording runs only while a key is held down: press, speak, release, done. It borrows its name from two-way radios.
- [Voice activity detection](https://flit.fyi/glossary/voice-activity-detection): Voice activity detection (VAD) is the technique of detecting when someone is speaking versus when there is silence or background noise. It lets software start and stop recording automatically.
- [Wake word](https://flit.fyi/glossary/wake-word): A wake word is a spoken phrase that turns a listening device on, like "Hey Siri" or "Alexa". A small always-on model listens for that one phrase and ignores everything else until it hears it.
- [Accessibility permission](https://flit.fyi/glossary/accessibility-permission): Accessibility permission is the macOS setting that lets one app read and control the interface of other apps. Dictation tools ask for it because it is how they type text at your cursor in whatever app you are using.
- [Speech-to-text](https://flit.fyi/glossary/speech-to-text): Speech-to-text (STT) is the technology that converts spoken audio into written words. It is the umbrella term covering live dictation, file transcription, captioning, and voice commands.
- [Automatic speech recognition](https://flit.fyi/glossary/automatic-speech-recognition): Automatic speech recognition (ASR) is the machine-learning field, and the class of models, that turns audio of human speech into text. ASR models are the engine inside every dictation and transcription product.
- [Whisper](https://flit.fyi/glossary/whisper): Whisper is a family of open-source speech recognition models released by OpenAI in 2022, trained on 680,000 hours of audio and covering about 99 languages. Because the weights are freely available, Whisper became the engine inside many local transcription and dictation tools.
- [Parakeet](https://flit.fyi/glossary/parakeet): Parakeet is a family of open-source speech recognition models from NVIDIA, built on a transducer architecture, which can emit words as audio arrives. That makes it a common engine inside live dictation tools, where Whisper is built to read a whole chunk first.
- [Neural Engine](https://flit.fyi/glossary/neural-engine): The Neural Engine is the part of an Apple silicon chip built to run machine-learning models efficiently, alongside the CPU and GPU. It is why a laptop can run speech recognition continuously without heat, fan noise, or a dead battery.
- [Streaming transcription](https://flit.fyi/glossary/streaming-transcription): Streaming transcription shows words on screen while you are still speaking, rather than after you stop. The alternative, batch transcription, processes the whole utterance at once and shows the text at the end.
- [Language identification](https://flit.fyi/glossary/language-identification): Language identification is the step where speech software works out which language is being spoken before, or while, it transcribes. It is what lets a multilingual tool switch languages without the user changing a setting.
- [Word error rate](https://flit.fyi/glossary/word-error-rate): Word error rate (WER) is the standard measure of speech recognition accuracy: the number of words a model got wrong, divided by the number of words actually spoken. A WER of 5% means about one word in twenty was substituted, dropped, or invented.
- [Hallucination](https://flit.fyi/glossary/hallucination): In speech recognition, a hallucination is text the model produces that nobody said: a plausible phrase invented from silence, noise, or a fragment too short to transcribe. It is the insertion error taken to its extreme.
- [Latency](https://flit.fyi/glossary/latency): In dictation, latency is the time between the end of your speech and finished text appearing at the cursor. It is the number that decides whether a tool feels instant or feels like waiting.
- [Speaker diarization](https://flit.fyi/glossary/speaker-diarization): Speaker diarization is the process of working out who spoke when in a recording, so a transcript can be labeled by speaker. It answers "who said this?" rather than "what was said?".
- [Disfluency](https://flit.fyi/glossary/disfluency): A disfluency is any break in fluent speech: fillers like "um" and "uh", repeated words, false starts, and self-corrections. Natural speech is full of them; finished writing has none.
- [Formatting pass](https://flit.fyi/glossary/formatting-pass): The formatting pass is the step after speech recognition that turns a raw transcript into text a person would have typed: punctuation, capitalization, numbers as digits, fillers removed, and a tone suited to where the text is going. It is where most of the difference between dictation tools lives.
- [Verbatim mode](https://flit.fyi/glossary/verbatim-mode): Verbatim mode is a dictation setting where the output is exactly what you said, with no rewording, tone adjustment, or cleanup beyond basic recognition. It exists because some text must survive intact.
- [Spoken punctuation](https://flit.fyi/glossary/spoken-punctuation): Spoken punctuation is saying the name of a mark or symbol, like "comma", "open paren", or "new paragraph", and having the dictation tool type the symbol instead of the word. The broader set of such phrases is usually called spoken commands.
- [Text expansion](https://flit.fyi/glossary/text-expansion): Text expansion replaces a short trigger with a longer saved text: an address, a signature, a canned reply. In voice tools, the trigger is spoken ("insert my scheduling link") and the full text is typed for you.
- [Personal dictionary](https://flit.fyi/glossary/personal-dictionary): A personal dictionary is the list of words a dictation tool has been taught to spell your way: names, products, jargon, and anything the speech model would otherwise write as the most probable English. It is the single most effective fix for the errors that repeat.
- [Tone matching](https://flit.fyi/glossary/tone-matching): Tone matching is a formatting feature that writes the same dictated words differently depending on where they are going: lowercase and loose in a chat app, punctuated and complete in an email, untouched in a terminal. The linguistic term for the level of formality is register.
- [Words per minute](https://flit.fyi/glossary/words-per-minute): Words per minute (WPM) measures text production speed. Conversational speech runs around 120 to 160 WPM, while composing original text at a keyboard averages roughly 31 to 40 WPM, which is the gap dictation exploits.
- [On-device processing](https://flit.fyi/glossary/on-device-processing): On-device processing means the speech recognition model runs on your own computer, so audio is transcribed locally and never uploaded. The alternative is cloud processing, where audio is sent to a server to be transcribed.
- [Local LLM](https://flit.fyi/glossary/local-llm): A local LLM is a language model that runs on your own computer rather than on a vendor’s server. In dictation tools it is the model behind the formatting pass: fixing punctuation, removing fillers, and matching tone, without the transcript ever leaving the machine.
- [Whisper large-v3 turbo](https://flit.fyi/glossary/whisper-large-v3-turbo): Whisper large-v3 turbo is a speech recognition model from OpenAI, released on 1 October 2024. It is Whisper large-v3 with the decoder cut from 32 layers to 4, which makes it much faster at a small cost in accuracy.
- [Cohere Transcribe](https://flit.fyi/glossary/cohere-transcribe): Cohere Transcribe is an open-source speech recognition model from Cohere, released in March 2026. It has 2 billion parameters, takes audio in and gives text out, and supports 14 languages.
- [Qwen3-ASR](https://flit.fyi/glossary/qwen3-asr): Qwen3-ASR is a family of open-source speech recognition models from Alibaba’s Qwen team, released on 29 January 2026. It recognizes 30 languages and 22 Chinese dialects, and identifies which one is being spoken.
- [MLX](https://flit.fyi/glossary/mlx): MLX is an open-source array framework for machine learning on Apple silicon, made by Apple’s machine learning research team. It is what many language models and speech models use to run on a Mac’s own chip.
- [Core ML](https://flit.fyi/glossary/core-ml): Core ML is Apple’s framework for running machine learning models inside an app, on the device. It uses the CPU, the GPU and the Neural Engine, and needs no network connection to make a prediction.
- [Quantization](https://flit.fyi/glossary/quantization): Quantization is storing a model’s numbers with fewer bits each, for example 4 or 8 bits where the original used 16 or 32. It makes the model smaller and lighter on memory, usually at a small cost in accuracy.
- [Real-time factor](https://flit.fyi/glossary/real-time-factor): Real-time factor (RTF) is the time a speech recognition system takes to process audio, divided by the length of that audio. An RTF of 0.5 means one minute of speech is transcribed in 30 seconds; below 1 is faster than real time.

## Optional

- [Changelog](https://flit.fyi/changelog): every change, week by week
- [Blog](https://flit.fyi/blog)
- [Full page inventory for LLMs](https://flit.fyi/llms-full.txt)