Speechy vs Wispr Flow

Wispr Flow is the best known dictation app, and a good one. But it sends every word you say to the cloud, it does not show your words while you speak, and it only bills monthly or yearly. Speechy does all of its dictation on your Mac, and it adds a long list of things Wispr Flow does not do. Here they are, with real examples.

At a glance

Your voice never leaves your Mac

Wispr Flow's own data page says transcription "always occurs on the cloud", and its help center says you need an internet connection to dictate. On the Free and Pro plans, using your dictations to improve their models is on by default. You can switch that off, but your audio still goes to their servers every time you speak.

Speechy transcribes with speech models that run on your Mac's own chip: 15 of them, from NVIDIA's Parakeet (the default) to Apple's own model and Whisper. What you say is never sent to a cloud AI, and dictation keeps working on a plane, on hotel Wi-Fi or with no Wi-Fi at all.

Speechy's Models page, listing on-device voice models from NVIDIA, Apple and Whisper

See your words while you speak

Wispr Flow types the finished text after you stop talking, so you only find a misheard word once it has landed. Speechy shows your words in a small pill as you speak. Pick the look you like: a compact pill, a wide pill with your words, a Dynamic Island style bar or a one-line ticker.

Speechy's four recording styles: Compact, Wide, Dynamic Island and Ticker

Mix languages in one dictation

Wispr Flow's help center says it detects "one language per dictation, not per word", and recommends picking the language you will speak. Speechy can listen for several at once. Pick your languages, turn on Multiple languages in one dictation, and Speechy works out the language again after every pause, on your Mac.

Speechy's language settings, with Multiple languages in one dictation

Only your voice gets typed

Wispr Flow has no setting for other people talking near you. Its docs suggest a closer or noise cancelling microphone.

Speechy has Only My Voice. Read one sentence aloud for about 10 seconds, and Speechy learns what you sound like. After that, words from a colleague behind you, the TV or a speakerphone are left out, and Speechy keeps learning your voice as you use it. Someone talking over you at the very same moment can still slip through, but everyday background chatter does not.

Only My Voice: read one sentence aloud and Speechy learns your voice

Built for Claude Code and Codex

Wispr Flow's developer features are tagging files in the Cursor and Windsurf chat panels and spelling variable names in some editors. It has nothing for answering your agents. Speechy puts Claude Code and Codex in your Mac's notch:

• Answer without switching windows. When an agent asks a question, wants permission to run a command or shows you a plan, it lands in the notch. Press 1 to allow or 2 to deny, J and K to move between them and E to clear one. Answered too fast? Esc takes it back within 2 seconds.
• Watch your plan limits. Your Claude and Codex usage sits beside the camera, read straight from the tools, with no keys to paste. The Usage tab shows the 5 hour and weekly windows.
• Talk to an agent by name. Hold the key and say "api, run the migration again on staging", and it goes to that project's agent.
• Read replies right there. Replies show formatted, with tables and code. Drop in up to 6 images, or drag the corner to make the chat bigger.
• Name files out loud. Turn on Reference coding files, and the file names you say become @file references in Claude Code for VS Code.

A Codex permission request in Speechy's notch, with Allow and Deny

Claude and Codex plan usage beside the camera

Talking to the api agent from Speechy's notch

Pay once, if you like

Wispr Flow Pro costs $15 a month, or $144 a year, and there is no lifetime plan. The free plan gives you 2,000 words a week on a computer.

Speechy Lifetime is a single payment, starting at $99 for the first 10 buyers. If you would rather subscribe, Pro is $12.99 a month or $119.88 a year. See pricing.

Everything else Speechy does

Here is the rest of Speechy, with real examples. Every "Speechy types" box is the app's own output for that sentence, taken from Speechy's test suite.

It cleans up the way people talk

Speechy drops filler words, stutters and false starts on your Mac, with no AI model and nothing to set up.

It keeps up when you change your mind

Say "sorry", "I mean", "make it" or "or rather", and Speechy swaps the old time, date, amount or name for the new one. "Make it work" and "sorry I'm late" are left alone.

Lists, without touching the keyboard

Count your points out loud, or say "bullet", and Speechy writes the list. In Mail, Notes, Pages and Word the dashes become bullets.

Numbers, money and times, written properly

Punctuation and new lines when you ask

Emails come out shaped like emails

Start with a greeting and end with a sign-off, and Speechy puts each on its own line. It skips this in chat apps, terminals and code editors, where you would not want it.

Your words, spelled your way

Add names and jargon to your dictionary, fix a word Speechy keeps mishearing with a replacement (in every app, or only in one), and save snippets for things you say often. Say "insert" and the snippet's name, and the saved text is typed.

Speechy's dictionary: words, replacements and voice snippets

It spells what is on your screen

With App Context on, the names in the window you are dictating into become spelling hints, so a file, a person or a product on screen comes out right. It all stays on your Mac, password fields are always skipped, and you can leave out any app.

Context you control: the names Speechy used from your screen, and the apps it leaves out

Undo a dictation, or throw one away

Pasted into the wrong window? Press ⌘⌥Z within five minutes and Speechy removes it and puts back anything it replaced. Changed your mind while talking? Press ⌘Esc to drop the take, so nothing is typed or saved.

Speechy's shortcuts: Fn to dictate, ⌘⌥Z to undo, ⌘Esc to discard

Paste, type or just copy, and send

Speechy pastes by default, then puts your clipboard back the way it was. It can type the words out instead, or leave them on the clipboard. Turn on Auto submit and it presses Enter (or ⌘Enter) for you, so a Slack message sends the moment you let go.

Speechy's output settings: paste method, clipboard and auto submit

Music pauses while you talk

Set Background audio to Pause media, and whatever is playing pauses while you dictate, then carries on when you are done. Speechy only resumes what it paused.

Help when the mic is wrong

If Speechy hears nothing, it says so and plays your recording back, so a muted headset is obvious in a second. One click opens the microphone picker and a live input meter.

A history that stays on your Mac

Search everything you have dictated with ⌘K, copy it all as Markdown or export it, and play back the audio. Deleted entries wait in Recently deleted until you empty it. You choose how much to keep, and when recordings delete themselves.

Stats that show the time you saved

Home shows your average speed, words dictated, dictations, days active and the time you saved compared with typing at 40 words a minute. The Stats page adds streaks, where your words go and your golden hour, and the Speechy pass turns it into a card you can share.

Light on memory

Speech models free their memory after 15 minutes idle (or 5, 60, or never), then reload as you start talking. With the default model that takes Speechy from about 1.2 GB to 60 MB.

A whole email from one sentence

Turn on Smart Polish with Apple Intelligence or the downloadable Qwen model, then start with "draft", "compose" or "write": "draft an email to Sarah saying the deck is delayed to Thursday". Speechy writes a greeting, a few short paragraphs and your sign-off, without inventing facts. "I need to draft the email later today" stays a normal sentence.

Small things that add up

• A menu bar menu to dictate, open your history or dictionary, or check for updates.
• Hold Fn to talk, or tap it to talk hands-free.
• Automatic updates, and a What's New tour when something new arrives.

Where Wispr Flow is better

• More devices. It runs on Windows, iPhone and Android, and syncs your dictionary and snippets between them. Speechy is Mac only for now.
• Older Macs. Because the work happens in the cloud, it runs on Intel Macs and Macs with little memory. Speechy needs Apple silicon.
• Teams. It has team plans with shared dictionaries, SSO and compliance reports such as SOC 2.
• Rewriting. Command Mode can rewrite selected text on request. Speechy's Smart Polish fixes slips but keeps your words.
• A free plan. 2,000 words a week. Speechy has no free plan.

Switching from Wispr Flow

Speechy can bring over the words, replacements and snippets you added in Wispr Flow. Open Settings, go to Dictionary and choose Import. It also reads Superwhisper, Monologue, Aqua Voice and Willow Voice.

Importing a dictionary from other dictation apps into Speechy

The short version

Choose Wispr Flow if you need it on Windows or your phone, or across a team. Choose Speechy if you want your voice to stay on your Mac, to see your words as you speak, to mix languages, to keep other voices out, to run your coding agents from the notch, and to pay once.

Wispr Flow details checked on 14 October 2026 on its pricing page, data usage page and help center. Prices and features change, so check their site before you decide.