Dictate in any app · Media
CapCut auto-captions your video and leaves the description, hooks and titles to you. Hold a key and talk: Typally transcribes and types it into CapCut without you touching the keyboard.
We make Typally, so treat this as a vendor's guide. Where CapCut has a built-in option we say so, including when it is the better choice.Automatic captioning of speech in your footage, plus text-to-speech. Both operate on the video, not on your writing.
Short-form video lives or dies on the hook and the caption, both of which are written text. Editors spend hours on cuts and thirty seconds on the words that determine whether anyone watches past the first second.
In practice people use it for: On-screen text and hooks, video descriptions, script drafts before filming, and caption copy for posting.
Typally runs in the background and types into whatever window has focus, so there is nothing to install inside CapCut:
Windows or macOS, then sign in. No card for the free tier.
Put the cursor in the field you are about to fill — CapCut decides where the text lands, not Typally.
Say the whole thought, then let go. No time limit.
Auto-captions transcribe what is in the footage. They do not help you write the script, the hook or the post copy.
Typally is for the writing around the edit — the script before you film, the hook, the description afterwards. CapCut captions what is already in your footage; it cannot help you decide what to say. Speaking the script first also lets you hear whether the hook works before you spend an hour filming it.
A creator who used to improvise on camera speaks the script first and listens back. Two of the three hooks are obviously weak when heard aloud, which saves filming them.
Dictate the script before you film. Saying it out loud first tells you whether the hook works far faster than filming and rewatching does.
Auto-captions transcribe what is in the footage. They do not help you write the script, the hook or the post copy.
Yes, it captions speech in your footage. That is transcription of the video, not dictation of your writing.
Before filming — scripting — and after, in the description and post copy.
Yes. Text elements are ordinary fields once selected.
There is a permanent free tier of 100 minutes a month. Pro costs $7.99/month and raises the limit.
Also dictate in: DaVinci Resolve · Adobe Premiere Pro · YouTube · see all apps