Real-time voice to text for Mac

70 milliseconds. That's how long it takes for your spoken words to become text. No cloud round-trip, no buffering, no waiting. Just speak and it's there.

Messages
S

Need the status update before the standup — can you send it quick?

Done. Sprint velocity is up 15%, we closed 3 blockers yesterday, and the new auth flow ships Friday.

SpeakingFn
100%
Offline & private
5
Languages supported
70ms
Transcription speed
0
Data sent to the cloud

How real-time voice to text works

Three steps. No setup. No account.

1

Hold your hotkey

Press and hold the key you choose (default: Right Option).

2

Speak naturally

Talk at normal speed. The speech model runs locally on your Mac.

3

Release — 70ms later, it's text

Your words are transcribed and pasted into your active app before you even move your hand.

Speed

Why 70ms matters

Cloud-based dictation adds network latency, server processing time, and response delays. Just Parley runs entirely on your Mac — so your words appear the moment you stop speaking.

No network latency

Cloud dictation tools make a round trip to a server. That's 200-800ms of latency before you even get a result. Just Parley processes locally in 70ms. The difference is night and day.

Cloud dictation
200-800ms
Just Parley
70ms

No buffering or queueing

Cloud services throttle, queue, or disconnect during peak hours. Just Parley runs on your Mac's CPU — consistent speed, every time, no matter what.

70ms

every time, guaranteed

Instant paste

The moment transcription finishes, text is pasted into your active app. No confirmation dialog, no intermediate window. Hold key, speak, release, done.

SlackSounds good, let's go with option B...
MailHi team, just wanted to check in on...
DocsThe quarterly results show a clear...

100% offline

No internet needed. No audio uploaded. No server to depend on. Your voice stays on your Mac, and the model runs on your CPU.

100% offline

Data sent to the cloud

Speed without compromise

70ms transcription

From the moment you stop speaking to the moment text appears. No spinner, no delay. This is what real-time actually means.

100% offline & private

No cloud means no latency from network calls, no privacy risks, and no dependence on servers that might be slow or down.

5 languages

English, Chinese, Japanese, Korean, and Cantonese — all at the same 70ms speed, all processed locally.

Works in every app

Slack, VS Code, Notion, Mail, Chrome — clipboard paste means it works everywhere. No app-specific plugins.

See it in action

Messages
M
Mike11:42 AM
Quick question — what was the conversion rate last week?
11:43 AMYou
It was 4.2%, up from 3.8% the week before. The new landing page is definitely making a difference
Y
Dictating with Just Parley

70ms. That's real-time.

One-time purchase. No subscription. No cloud.

Early pricing
$29
one-time purchase
Works in every Mac app
100% offline — your voice stays on your Mac
70ms transcription speed
5 languages: English, Chinese, Japanese, Korean, Cantonese
Use on up to 3 Macs
Free updates for life

30-day money-back guarantee.

Frequently asked questions

How fast is the transcription really?+
About 70ms after you stop speaking. This is the time from audio capture to text appearing in your active app. There's no spinner, no progress bar — it's functionally instant.
Why is it so fast?+
Because there's no cloud. Just Parley runs the SenseVoice speech model directly on your Mac's CPU. No network round-trip, no server queue, no API rate limiting.
Does speed come at the cost of accuracy?+
No. SenseVoice is a state-of-the-art model with automatic punctuation and capitalization. Speed and accuracy are not a trade-off here.
Does it work offline?+
Yes, completely. The speech model runs on your Mac's CPU. No internet needed, and no audio ever leaves your computer.
What languages does it support?+
English, Mandarin Chinese, Japanese, Korean, and Cantonese. All are processed locally at the same speed.
Is there a money-back guarantee?+
Yes — 30 days. If the speed doesn't impress you, you get a full refund.