1.4Open source · launching soon

Open-source dictation.10× faster than Wispr Flow.

Speak anywhere you type. OpenFlow turns your voice into clean, ready-to-send text about 50 milliseconds after you let go of the key on an Apple-silicon Mac — entirely on your own device.

macOS Windows Linux · soon Android · beta

Release the key. Watch the text land.

Same sentence, real speed. Timers start when the key comes up.

OpenFlow0 ms
Wispr Flow0 ms
Benchmarks

Measured, not promised.

Every number comes from our own test runs on real recordings. Quality is judged blind, in both orders. Hover any bar for the details. Public test sets, Canto and Voice Arena comparisons →

0×
Faster than Wispr Flow
On Apple-silicon Macs: 54 ms vs ~520 ms (9.6×)
0%
On your device
No audio or text leaves it. Works offline.
0
Better clean-up
Net, vs Wispr Flow on the same transcripts
0
Common Voice WER
16,334 public clips. Wispr's Canto reports 9.2%
10×faster
Speed

Key release to final text

Median, milliseconds · lower is better

OpenFlow 1.4: 30 real recordings replayed in real time on an M4 Pro, two runs (55 and 53 ms). Dictations up to 20 seconds get a second, whole-recording pass for accuracy, which is most of the 54 ms. Slowest 10%: 170 ms or more. Wispr Flow: ~520 ms, measured by Elliot Arledge on his own clips, not by us.

Quality · blind judge

Which output reads better?

Share of items, averaged over both A/B orders

Accents

Accented English, 13 accents

EdAcc word error rate · lower is better · 477 held-out utterances

Research result, not shipped yet: our 110M speech model, distilled from NVIDIA's 0.6B recognizer on 155 hours of public audio. Better than the stock model on 12 of 13 accents at the same speed, but it wrote some numbers as unknown tokens, so phones use the stock 110M for now.

Engineering

Where the speed comes from

OpenFlow vs Wispr Flow

Same idea. Your device.

Wispr Flow is excellent, and it runs in the cloud. OpenFlow does the whole job on your own machine, and the code will be yours to read.

OpenFlowWispr Flow
Open sourceAt launchNo
Where your voice is processedOn your deviceWispr's servers
Works offlineYesNo
Key release to text (median)54 ms~520 ms (reported)
macOS and WindowsYesYes
LinuxWith the open-source releaseNo
iPhone and AndroidAndroid beta today · iPhone in testingYes
Your names and jargonReads names on your screen, on the device; boosted while it listens; imports a Wispr dictionaryDictionary and context awareness
PriceFree, no word limitsFree with weekly limits · Pro $12/user/mo

Wispr Flow details from wisprflow.ai/pricing and Wispr's privacy documentation, November 2026.

Platforms

Works where you work.

One engine, tested on every platform with a real recording — not a mock.

Download

macOS

Menu-bar app. Hold fn, talk, let go. Apple silicon or Intel, macOS 12 and later.

Fastest engine on Apple silicon with macOS 14+
Download

Windows

Hold Right Ctrl, talk, let go. Windows 10 and 11, 64-bit. Nothing else to install.

Tested on fresh Windows machines
Soon

Linux

Same engine and tests; runs on NVIDIA (CUDA), Vulkan or the CPU. Ships with the open-source release.

Passes a real dictation on every code change
Beta

Android

A voice keyboard running NVIDIA Parakeet 110M and our clean-up model on the phone. iPhone is in testing.

7.4 s of speech to text in 554 ms
How it works

It finishes while you're still talking.

That's the trick behind the speed: by the time you let go, almost all of the text is already written.

01

Hold and speak

Audio streams in 100 ms pieces while you hold the key.

02

Hear

NVIDIA Parakeet recognizes speech on-device, with your own words boosted as it listens.

03

Clean up

A small model fine-tuned for dictation removes ums and false starts, adds punctuation, and matches the app.

04

Land

It rewrites every half second as you talk, so the text is ready the moment you let go.

Open source

Fully open. Launching soon.

We're opening the code, the apps, the public models and the benchmark suite, so every number on this page can be checked on your own machine. The license will be announced with the release.

GitHub · coming soon
  • The engineRust core for Windows, Linux, Intel Macs and phones; native Apple-GPU engine for Apple silicon.
  • The appsmacOS and Windows today; Linux and Android with the release; iOS on the way.
  • Public modelsThree rewriters (1.7B, 1.2B, 350M) trained only on public data, plus our distilled 110M speech model (research preview).
  • BenchmarksThe test sets, the blind-judge harness and the latency suite behind every chart.
  • A seven-part build guideHow it was built, step by step, including what didn't work.
Download

Free. One click.

Download, open, hold a key and talk. Everything runs on your own computer or phone; no account needed.

Mac

Any Mac · macOS 12 or later
Download for Mac
180 MB, one app for every Mac. It opens in seconds and fetches its speech models while you set it up (2.3 GB on Apple-silicon Macs with macOS 14+, about 1–1.4 GB on older or Intel Macs).
  1. Open the downloaded file and drag OpenFlow into Applications.
  2. Open OpenFlow. The first time, macOS says “Apple could not verify ‘OpenFlow’ is free of malware”. That’s because OpenFlow isn’t notarized by Apple yet (our developer account is waiting for Apple’s approval). Click Done, then open System Settings › Privacy & Security, scroll down and click Open Anyway. You only do this once.
  3. Allow the microphone, Accessibility and Input Monitoring when asked. Then hold fn, talk, and let go.
Prefer Terminal? One line installs it, with no Open Anyway step.
curl -fsSL https://rajatdandekar--openflow.modal.run/install.sh | bash

Windows

Windows 10 or 11 · 64-bit · nothing else to install
Download for Windows
1.2 GB · for Intel and AMD PCs · the text appears as you let go
  1. Open the downloaded file, click Extract all, then open openflow.exe.
  2. If Windows shows a blue SmartScreen box, click More info › Run anyway (first time only).
  3. When it says OpenFlow is ready, click into any text box, hold Right Ctrl, talk, and let go.
Prefer PowerShell? One line installs it with a Start-menu shortcut.
irm https://rajatdandekar--openflow.modal.run/install.ps1 | iex

Android beta

Android 9 or later · 64-bit phone · about 0.5 GB of speech models, downloaded once
Download for Android
15 MB · open this page on your phone · Google Play version coming soon
  1. Tap the button on your phone and install the app (allow installs from your browser when Android asks).
  2. Open OpenFlow and follow the four steps: microphone, models, turn on the keyboard, switch to it.
  3. In any app, switch to the OpenFlow keyboard, hold Hold to talk, speak, and let go.

iPhone soon

iOS 17 or later · a voice keyboard like the Android app
Coming to TestFlight
Working in testing; waiting for Apple to approve our developer account.
  1. Testers get an email invite to TestFlight, Apple's beta app.
  2. Install TestFlight, tap the invite, and install OpenFlow.
  3. Turn on the OpenFlow keyboard in Settings and talk in any app.
Linux · with the open-source release
How to use

Click, hold, talk. It types where your cursor is.

Works in any app with a text box: Slack, Gmail, Notion, ChatGPT, Notes, Word, your code editor.

01

Hold fn and talk

Click into any text box, hold fn (🌐) on a Mac or Right Ctrl on Windows, speak naturally, let go. The Vizuara flower turns while you talk.

02

Hands-free

Tap fn twice quickly to keep listening without holding; tap fn once to stop. Good for long emails and notes.

03

Names spelled right

Replying to someone? OpenFlow reads the names on your screen (on your Mac only, never saved) and spells them correctly. Turn it off in the ◉ menu.

04

First launch on a Mac

A setup window walks you through it: allow the microphone and switch OpenFlow on in Accessibility. After an update, if it's already on, switch it off and on once.

Something not working? Click ◉ in the menu bar: it lists anything that needs fixing with a one-click button. If text didn't appear, it's on your clipboard: press ⌘V. Restart engine in the same menu clears anything stuck. On Android, switch to the OpenFlow keyboard, hold the bar to talk, or type with the keys. Everything runs on your device; your voice never leaves it.

Credits

Built on the shoulders of phonon.

OpenFlow started from Elliot Arledge's open-source phonon. Here's what it showed, and what we added.

Elliot Arledge's phonon showed that NVIDIA Parakeet plus a small fine-tuned Liquid AI rewriter can beat Wispr Flow on a Mac — he measured 65 ms for phonon against about 520 ms for Wispr Flow on the same clips.

We rebuilt his recipe from scratch. In blind tests on our own dictations it matched or beat his released 1.7B model. Then we kept going. Thank you, Elliot.

  • Finishes while you talk54 ms median from key release to text on an M4 Pro, including a whole-recording accuracy pass (phonon reported 65 ms on an M4 Max).
  • Cleaner restarts and repeats"Tuesday, no sorry, Wednesday" becomes "Wednesday": +15% on a restart test set.
  • Names from your screen, spelled rightNew in 1.4 on Mac, Windows and the Android keyboard: OpenFlow reads the names around where you dictate (on the device, never saved) and uses them while it listens and cleans up. On our benchmark, names right go from 74% to 93% when they are on screen.
  • Beyond Apple siliconA portable Rust engine for Windows, Linux, Intel Macs and Android.
  • Our own speech model for phones (research)Distilled from Parakeet 0.6B on public audio; better on 12 of 13 accents. It ships once it writes numbers reliably.
  • Public models, open releaseModels trained only on public data; the full code is coming soon.
The fine print

Where we're not there yet.

Long recordings

On long real recordings, Wispr Flow's cloud recognizer still hears better and wins end to end in our blind tests, mostly on misheard words. Closing that gap is our next milestone.

English only, for now

OpenFlow is English-only today; Wispr Flow supports over 100 languages. On older Intel Macs and PCs, the portable engine takes one to two seconds.

How we measured quality

The quality results use a model personalized on the author's own dictations, which stays private. The downloadable public model is trained only on public data and scores lower on the same transcripts.

Your voice. Your device. Two milliseconds.

OpenFlow is in preview. The open-source release is coming soon.

Download for free