Instant Mac dictation · Open source

Speak. Your Mac types — instantly.

Faster and more accurate than built-in dictation — in any app. Teach it your vocabulary or use a compatible fine-tuned model.

Workspace Local agent

Prompt

Describe the change…

Right ⌥ Hold anywhere Speak naturally Text lands at the cursor
Scroll

It never leaves your Mac.

No account and no upload. Downloads happen once; the model runs on your own silicon.

It never picks a language.

Others pick one language and translate the rest away. This one keeps them all.

It feels instant.

Twelve seconds of speech, transcribed in under one second.

Teach it once.

Add a name, term, or jargon once. It remembers from then on.

Voice shortcuts

Say a phrase.
Insert anything.

Turn a short spoken trigger into a URL, signature, address, reusable reply, or any text you type often. Shortcuts stay on your Mac and work wherever the cursor is.

Voice shortcut Listening
You say
shortcut github
Mac types

https://github.com/yourname

Saved locally · available in every text field

The idea

It never cuts the sentence.

Chunked transcription slices audio into pieces, and the cuts land mid-word — exactly where a mixed sentence breaks. WhisprStream re-reads the whole utterance instead, several times a second.

Chunked · the cut lands mid-word

Whole · read again from the start

Bring the right model

Streaming is a behavior, not a model requirement.

Use another supported transcription model or a compatible fine-tuned checkpoint. Even when the model only returns a finished transcript, WhisprStream repeatedly re-reads the growing utterance and settles the stable words into a live stream.

Compatible ASR checkpoint Base · fine-tuned
Pass 01
Pass 02
Pass 03
One continuous dictation stream
0.6B

Parameters. Small enough to stay resident and warm.

0.9s

To transcribe twelve seconds of bilingual speech.

0bytes

Leave the machine. There is no server to leave for.

MIT licensed

Read every line.

Software that listens to you should be software you can audit.

Get the app ZIP from Releases View on GitHub