Bind a dictation shortcut, hold it, say what you mean, let go. The text lands at your cursor in any app: cleaned up, punctuated, and spelled the way your team writes.
No recorder window, no transcript to paste. The words are typed where your cursor was, in whatever app you were holding the key over.
Hesitations out, punctuation in, in the same request. A dictation costs one action's worth of your monthly credits, cleanup included.
Generic dictation guesses at your nouns. Khint primes the recognizer with your agent and workflow names, so ticket keys and product terms come out the way you mean them.
Any agent can listen instead of reading a selection.
A whole routine can start from a sentence you say.
With the palette open, the same gesture fills the idea bar.
Dictation is opt-in: it does nothing until you bind a shortcut. The whole story, also spelled out on our privacy page.
The mic opens on key-down and closes on release. Your OS recording indicator lights exactly while you hold the key, never outside it.
The clip is transcribed on Khint's servers by a speech provider with zero data retention: nothing stored, nothing trained on. Khint keeps no copy of the audio either.
No on-device model, no setup, no warm-up. It works the same on an ordinary work laptop as on a new Mac.
A dictation costs one action's worth of your monthly credits, cleanup included. No separate voice meter, no per-minute pricing.
Set a dictation shortcut in Khint, hold it, speak, and let go. The transcript is typed at your cursor in whatever app you were in: Mail, Slack, Jira, a code editor, anywhere you can type. No recorder window, nothing to paste, and no model to download first.
Yes. When you dictate plain text, hesitations and filler words are dropped and punctuation is fixed in the same pass, so what lands reads like something you wrote. If the cleanup can't run, you still get the raw transcript rather than nothing. Dictations that feed an agent, a workflow, or the idea bar skip the cleanup: the agent reads through hesitations itself, and skipping it keeps the run fast.
That's the part most dictation tools miss. Khint primes the recognizer with the names of your agents and workflows, so the proper nouns that matter in your work come out spelled the way you mean them: ticket keys like AUTH-112, product terms, project names.
Yes. Set an agent's input to Voice and its own shortcut becomes hold-to-speak: hold, describe, release, and the agent runs on your words, pasting its result back as usual. A workflow can start from your voice the same way, and it shows your transcript as the run starts, so you see what it heard before the steps land anywhere.
One dictation costs one action's worth of your monthly credit balance, cleanup included: it runs inside the same request. There is no separate voice meter and no per-minute pricing.
The microphone opens when you press the key and closes when you release it: your OS recording indicator lights exactly while you hold, never outside it. On release, the clip is transcribed on Khint's servers by a speech provider with zero data retention: audio and transcripts are not stored and not used for training. The provider is named plainly on our privacy page. Khint keeps no server-side copy of the audio.
No. There is no on-device model, so there is nothing to download and nothing to warm up, and transcription is just as fast on an ordinary work laptop as on a new Mac. Hold, speak, release: the text is back in a fraction of a second, however long you spoke.
Guided walkthroughs that run on this pillar, start to finish.