Skip to content
ZenVoice

100% on-device · for Mac

Say it messy. Send it clean.

Press a shortcut, speak, and your words land in any app. Transcribed and polished on your Mac, never in the cloud.

Launch price for the first 100 · $14.99 once · No subscription · On Windows? Join the waitlist

NotesFileEditFormatViewWindow
Tue 9:41
iCloud
All Notes
Work
Launch
Ideas
23 September 2026 at 9:41
Launch checklist
— Final QA pass on 0.5.0
— Record the product film
ZenVoice settings: the Recording HUD picker with Notch and Floating panel styles

73×

faster than real time

Parakeet V3 on an M5

0.4 s

to clean text

ZenPolish, per dictation

25

languages on your Mac

plus Hinglish

0 bytes

of your voice leave your Mac

no account, no cloud

Types into every app, Chrome and Electron included.

Films

See it, then hear it.

Every feature, chapter by chapter: cleanup, numbers, tone, agents, review, dictionary, languages, offline. Original score.

Take the 4-minute app tour →

01 · Cleanup

Finished text, not a transcript.

Say it the way it comes out. Fillers, false starts and repeated words are gone before the text lands, and “scratch that” takes back what you just said.
  • “um so uh can we move the the launch to thursday”Can we move the launch to Thursday?
  • “send it by friday, scratch that, thursday”Send it by Thursday.
How ZenPolish writes it →

02 · Speed

Faster than your fingers.

Your words appear as you talk. Parakeet V3, the default engine, runs at 73× real time, and ZenPolish cleans a dictation in about 0.4 s on an Apple M5.
2,000

23 min

saved a day

1.9 h

saved a working week

Typing at 52 words a minute, the average across 168,000 typists (Dhakal et al., 2018), against speaking at a relaxed 130. Your own words per minute are in Insights.

03 · Formatting

Written the way you’d type it.

Money, times, counts and email addresses are written by fixed rules, so “three thousand dollars” is always $3,000. And the tone follows the app: relaxed in Messages, polished in Mail.
  • Try it: pick an app and see the same sentence written for it.

You say

“hey are we still on for five pm”

Mail · Professional

Hello, are we still meeting at 5 pm?

“three thousand dollars”

$3,000

“meet me at one twenty”

1:20

“one hundred twenty chairs”

120 chairs

04 · Context

It reads the room, then forgets it.

When you dictate a reply, ZenVoice reads the window you're in, for that one dictation. Names in the thread come out spelled right, and the reply matches the thread's tone.

To: Anjali Mehta, Dev Patel · Re: Launch plan

Anjali: can we move the review to Friday?

I talked to Priyanka about it. The deck is ready.

Reads

The window around the text field: the thread, the recipient, the project.

Uses

Names in view spelled right, the thread's tone matched, file names spelled the project's way.

Keeps

Nothing. It is read for one dictation, then forgotten.

05 · Agents and terminals

Talk to your agents. Terminals get your exact words.

In a terminal, what you say is typed exactly: flags, dashes and all. In a prompt for a coding agent, your project's file names are spelled the way they are on disk.
  • Works in Terminal, iTerm, Ghostty and Warp, and with Claude Code, Codex, Cursor, VS Code and Xcode.

# you say: “git push dash dash force-with-lease origin main”

~/zenvoice $ git push --force-with-lease origin main

Exact wordsFlags keep their dashes, and nothing is reworded.

06 · Dictionary

It asks before it remembers.

Correct a word once and copy it, and ZenVoice suggests the fix: “Cooper Nettys → Kubernetes”. Add it, and it's right from then on. Nothing is learned without a yes.

07 · Languages

25 languages. And Hinglish.

Parakeet V3 speaks 25 European languages on your Mac, Whisper covers many more, and Hinglish Prime writes Hinglish the way people text it. Speak in one language and have it written in English, if you like.
Every model and its languages →

Said in Español

NVIDIA Parakeet V3

Canto para que me escuchen.

Press a language to hear it, and see it written as it's spoken.

08 · Your numbers

Counted on your Mac.

Words per minute, words dictated, time spent and fixes made, with a streak to keep. Insights are calculated from your history on your Mac and go nowhere else.

09 · Privacy

Nothing leaves your Mac. Check it yourself.

No account, no analytics, no cloud. Turn the Wi-Fi off and dictate: it works the same. ZenVoice goes online for two things only, and never while you dictate.
  • Downloading a model you pick, verified by SHA-256
  • Checking for signed updates
Read the full privacy statement →

Network monitor · ZenVoice

Dictations today

41

Sent while dictating

0 bytes

Every host ZenVoice ever contacts

  • huggingface.coModel downloadWhen you click Download
  • getzenvoice.comUpdate checkAbout once a day, if on
  • getzenvoice.comLicence activationOnly when you activate

None of them during a dictation. That's the whole list.

10 · Extras

Small things you’ll use every day.

Hold, tap or hands-free

Hold the shortcut to talk, tap to lock it on, or let it start when you speak.

Notch or floating

Your words appear as you speak, in the notch or in a bar at the bottom.

Review before inserting

The bar opens into a card: read it, fix a word, then insert.

Edit by voice

Select text and say “make it shorter” or “turn it into bullet points”.

Snippets

Say “insert my mailing address” and the whole block lands.

Spoken commands

“New paragraph”, “open parenthesis”, “thinking emoji” 🤔.

Paste the last one

⌃⌥V pastes your last dictation anywhere.

Audio History

Keep the recordings if you like, and play them back.

Recovery Inbox

If a dictation ever fails, the audio is kept so you can try it again.

14 models from 7 publishers, running on your Mac

NVIDIAOpenAI WhisperAppleQwenCohereZenPolishZenVoiceHinglish Prime

14 Models Available

Eleven speech engines and three Smart formatting models. Every download is pinned to a reviewed revision and checked by SHA-256 before it runs.

ZenVoice
  • Apple
    Speech
  • Parakeet
    V3
  • Parakeet
    V2
  • Nemotron
    3.5
  • Qwen3‑ASR
    0.6B
  • Cohere
    Transcribe
  • Whisper
    Turbo
  • Whisper
    Small
  • Whisper
    Tiny EN
  • Whisper
    Tiny
  • हHinglish
    Prime
  • Apple
    Intelligence
  • ZenVoiceZenPolish
    1.7B v2.2
  • Qwen 3.5
    2B

Benchmarks

Measured, not claimed.

Word error rate and speed on Common Voice Spontaneous 4.0 · 262 clips · 51 min, MacBook Pro M5. Lower WER is better.

Speech engine benchmark on Common Voice Spontaneous 4.0 · 262 clips · 51 min, MacBook Pro M5
EngineWERSegmented WERp50 decodep95 decodeReal time
NVIDIA Parakeet TDT 0.6B V3Lowest WER6.9%8.3%0.13 s0.37 s73×
NVIDIA Parakeet TDT 0.6B V27.3%9.3%0.12 s0.37 s73×
Whisper Large V3 Turbo8.2%9.8%1.00 s2.19 s11×
Cohere Transcribe10.8%12.5%1.93 s5.75 s5×
NVIDIA Nemotron 3.5 Multilingual 0.6B13.8%14.0%0.20 s0.60 s45×

How ZenVoice compares.

Against the apps people weigh it with, as each describes itself. If you need a phone app today, or you transcribe audio files, one of them may suit you better.

ZenVoice compared with Wispr Flow, Superwhisper and SpeakMac, as each describes itself on September 27, 2026
FeatureZenVoiceWispr FlowSuperwhisperSpeakMac
Where your speech is processedOn your MacIn the cloudOn your Mac or in the cloudOn your Mac
Works with no internetYesNoWith local modelsYes
Account neededNoYesNot for the free planNo
Price$14.99 once (launch price, first 100)Free up to 2,000 words a week, then $12–15 a monthFree, or $8.49 a month for Pro$29–39 once
PlatformsMac (Windows in the works)Mac, Windows, iPhone, AndroidMac, Windows, iPhone, AndroidMac
Own writing model, with a published benchmarkYesNoNoNo
Numbers, times and money written by fixed rulesYesNot statedNot statedNot stated
Tone that follows the appYesYesModes you pickStyles you pick
Choice of on-device speech models14 modelsNot statedYesNot stated
Project file names spelled right for agentsYesNot statedNot statedNot stated
Review before the text landsYesNot statedNot statedNot stated
HinglishHinglish PrimeNot statedNot statedNot stated
Keeps the audio if a dictation failsRecovery InboxNot statedNot statedNot stated
Transcribes audio filesNoNoYesYes

Competitors as each describes itself on its own site, checked September 27, 2026: Wispr Flow, Superwhisper, SpeakMac. Wispr Flow: “Transcription always happens in the cloud” (privacy page). Spotted something out of date? Tell us at hello@getzenvoice.com.

Pricing

Pay once. Yours forever.

Both plans cover two Macs, every model and every language. The only difference: how long you get new features.

Pro

Everything ZenVoice does today, on two Macs, with a year of new features.

$39.9962.5% offfor the first 100
$14.99once

Upgrade to Lifetime any time for the difference: $25.00 at launch prices.

  • 2 Macs
  • All 14 models and every language
  • Runs offline. Nothing leaves your Mac
  • 1 year of new features and new models
  • Bug fixes, UI fixes and macOS compatibility forever

Lifetime

Recommended

Every update we ever ship, including new features and new models.

$99.0060% offfor the first 100
$39.99once

Every update we ever ship, for one payment.

  • 2 Macs
  • All 14 models and every language
  • Runs offline. Nothing leaves your Mac
  • Every new feature and new model, forever
  • Bug fixes, UI fixes and macOS compatibility forever

Questions people ask before buying.

Does it work offline?

Yes. Dictation never needs the internet. ZenVoice goes online only to download a model you pick and to check for signed updates.

Is my voice used to train anything?

No. Your audio and your words never leave your Mac, so there is nothing to train on.

Do I need an account?

No. There is no sign-up and nothing to log in to.

Which Macs does it run on?

macOS 15 or later, on Apple silicon or Intel. Every model runs on Apple silicon; ZenPolish needs it, and Apple Speech needs macOS 26.

Does it work in every app?

It types into any text field: Mail, Slack, Messages, Notes, browsers, Chrome and Electron apps, code editors and terminals.

How is it different from the dictation built into macOS?

ZenVoice cleans up what you say, writes numbers and times by rule, matches the tone of the app, learns your words when you say yes, spells your project's file names for agents, and lets you pick from 14 models.

Is it a Wispr Flow alternative?

On a Mac, yes: your speech is processed on your Mac instead of in the cloud, there's no account, and you pay once. Wispr Flow also runs on phones, which ZenVoice doesn't; ZenVoice for Windows is in the works.

Why is it better at numbers and times?

Because rules write them, not a model's guess. “Three thousand dollars” is always $3,000 and “one twenty” in a time is always 1:20.

How big is the download?

The app is small; models download separately, and you pick which. The default speech engine, Parakeet V3, is 0.9 GB. Every model's size is on the Models page.

Does it speak my language?

25 European languages with Parakeet V3, many more with Whisper, and Hinglish with Hinglish Prime. Hindi in Devanagari isn't offered yet.

What's the difference between Pro and Lifetime?

Only updates. Pro ($14.99) includes a year of new features and models; Lifetime ($39.99) includes every one we ever ship. Both cover two Macs, and bug fixes and macOS compatibility continue for both.

Can I buy for a team?

Yes: one licence per Mac, from 5 Macs, and the price per Mac drops as the team grows. Over 100 Macs, talk to us.

Will there be a Windows version?

Yes, it's in the works. Join the Windows waitlist at getzenvoice.com/windows and we'll email you once, when it's ready. There's no iPhone version planned.

How it works

ZenVoice
Applications

Download ZenVoice

1

Parakeet V30.9 GB
Whisper Turbo0.5 GB
ZenPolish 1.7B v2.21.5 GB

Pick a model

2

⌃⌥Space

Press ⌃⌥Space and talk

3

ZenVoice

Download ZenVoice

Mac

Available

macOS 15 or later. Apple Speech needs macOS 26.

Windows

In the works

We’re building ZenVoice for Windows. Join the waitlist and we’ll email you once, when it’s ready. More about Windows →

Your email is used for this one message and nothing else.

Stop typing.
Start talking.

Available on macOS 15+ · Apple Silicon and Intel

Ask AI about this pageChatGPT ↗Claude ↗Perplexity ↗Grok ↗Markdown