Speech to textOffline

Speak. It lands where
you’re already typing.

Turn your voice into text across your Mac. Hold a shortcut, speak naturally, and Vocaldi types your words at the cursor using private, offline speech-to-text.

Try Vocaldi free

Speak.

Hold the shortcut or tap once for hands-free dictation.

Start dictating

⌥Space

Hold the shortcut from any text field, or tap it once for hands-free dictation.

Speak naturally

Talk as you normally would. Your audio is transcribed on your Mac, never sent to a server.

Stop, it’s typed

AT YOUR CURSOR

Release the shortcut, or tap again. Cleaned-up text lands where you were typing.

Both gestures are always live: hold the shortcut to record and release to insert, or tap once to start a hands-free session and tap again to stop. No mode to switch.

Automatically clean up the dictation.

Four levels, all on-device, from word-for-word to crisp. Vocaldi only ever removes fillers and stumbles. It never rewrites the words you actually said, and when audio is unclear it flags the word rather than quietly guessing.

CLEANUP · OFF

Um,I mean,we shouldjust,like,you know,ship it.

Cleansspacing + stutters only

Keep every word as spoken; only tidy spacing and stutters.

Clipboard Context: copy while you talk

Describing something on screen? Copy it mid-sentence. Vocaldi pins every copy, text or screenshot, to the exact word you were saying and drops it into the transcript right there. Built for feeding an AI chat real context without breaking your sentence.

Copy mid-sentence

⌘C

While dictating, grab anything from any app: a paragraph, an error message, a screenshot. Keep talking.

Pinned to the word

Each copy is timestamped against your speech and anchored to the exact word you were saying.

Inserted in place

IN YOUR TRANSCRIPT

When the transcript lands, every capture drops in right where you referenced it, as raw context.

Like the rest of Vocaldi, this happens on your Mac; captures go into the text you insert and nowhere else.

Stop typing what you could say.