Adding captions
+
Captions Word-level 100+ languages

Auto AI captions,
in 100+ languages

Upload your footage — ChatCut transcribes it into an editable transcript and lays word-level captions on the timeline, styled the way you want.

The transcript is
your caption track

Upload your footage and ChatCut transcribes it into an editable transcript — then lays word-level captions on the timeline, in sync with every word you see on the left.

chatcut-update Export 128.0
TranscriptAI
Speaker 10:00

This one is good. ChatCut is the best AI motion graphic generator ever since nothing else comes close. Alright, it's been a while.

Speaker 10:12

Lots of things have happened since we last spoke. We launched, we're in public beta, and we're trending on X.

Speaker 10:24

So, update number one. If you're our user, you already know ChatCut has incredible motion graphics features.

Speaker 10:34

Right now, after the AI generates the motion graphics, you can actually edit them by hand. You click it, get a toolbar, and select different fonts.

Speaker 10:48

You can change the size, the color, the timing — every layer stays live, so nothing is baked in.

Captions · English107 words
MediaEffects
AllVideoAudio
6:48
chatcut-update.mp4
Add media
00:00 / 00:11 ON
00:0000:0300:0600:09
V1Video 1
chatcut-update.mp4
A1Dialogue
take.wav
A2Music
music-bed.mp3

Upload the take.
ChatCut writes the words.

From footage to an editable transcript to styled, word-level captions — all on one timeline.

Upload it.
ChatCut transcribes it

Drop your footage into the media
pool — transcription starts on
upload, language auto-detected.

Add captions

The transcript is
the edit surface

The full transcript lands beside
your clip — every word timed and
editable, with the take right below.

Open the editor

Captions that land
on every word

Play the clip and captions roll
word by word — the transcript
lights up right on the beat.

Add captions

Restyle captions
on the timeline

Captions are a real track. Pick a
style — karaoke, clean, boxed, pop —
and every caption updates at once.

Try styles

One editor,
start to finish

Pull back and it's all one
workspace — transcript, player,
captions, timeline. Nothing leaves it.

Try ChatCut
AIHistory
Caption this take — word-level timing, auto language.
talking-head-take.mp40:33 · 4K · 54 MBUploaded
read_media · added to your media pool

Take received — starting transcription. Language auto-detected: English.

transcribe_audio · word-level timestamps
Transcribing… 54 words
Tell ChatCut what to change — @ to reference media
TranscriptMedia
Speaker 10:00

So um today I want to talk about uh how to actually make your videos look you know really professional.

Speaker 10:12

Um the first thing is like you gotta have good lighting.

Speaker 10:21

Uh and then you know the editing part is where the magic happens. Like cutting out all the dead air and keeping the energy tight.

CAPTIONS

Done
Style
AaPlain AaStory Yellow AaStudio Clean AaBubble Pop
Text
Captionyour videos look really…
FontInter
Font size52
Max chars / line18
Color
Text
Highlight word
Background
Position
PlacementBottom · Safe area
Effects
Shadow
StrokeOff
CCCaptions · EnglishSelect a caption to edit it in the inspector
0:000:080:160:240:33
C1Today I want to talk about…how to actually make…gotta have good lightingthe editing part is where…
Dialogue

Captions that work
like a real track

Generated from the transcript, so they're accurate on the first pass.

Word-level timing 100+ languages 20+ styles Editable transcript Timeline-ready Custom templates

Everything is built
on the transcript

From styled captions and speaker labels to translated subtitles, ChatCut transcribes your footage first and builds every caption feature on top.

Timeline

Captions, voiceovers, music, and effects line up on one timeline. Edit any of them and everything stays in sync.

Audio and Video support

Upload video or audio files. ChatCut transcribes them and generates captions, voiceovers, music, and sound effects on top.

Captions

Generate captions in one click to boost reach and engagement, with 11 presets and over 20 properties per caption.

Built on the transcript

Every word is timed and every speaker identified, straight from the transcript.

100+ Language support

Caption in over 100 languages with accurate transcription and translated subtitles for your audience.

Free

No credit card required

Get started
  • Starter credits included
  • Basic editing and exports
  • Try AI image, captions, music, and motion graphics
  • Upgrade when you need a monthly credit budget
$25 /month

Billed monthly

Get started
  • 100 credits / month
  • 200 credits / month
  • 800 credits / month
  • 1,200 credits / month
  • 2,000 credits / month
  • 3,000 credits / month
  • 4,000 credits / month
  • 5,000 credits / month
  • 7,500 credits / month
  • 10,000 credits / month
  • 100 credits / month
  • Seedance 2.0 (up to 166s of video)
  • GPT Image 2 (up to 454 images)
  • Nano Banana 2 (up to 312 images)
  • Motion graphics (up to 500 clips)
  • Motion graphics transparent export
  • AI music generation
  • All AI agent editing capabilities
$100 /month

Billed monthly

Get started
  • 400 credits / month
  • Seedance 2.0 (up to 666s of video)
  • GPT Image 2 (up to 1,818 images)
  • Nano Banana 2 (up to 1,250 images)
  • Motion graphics (up to 2,000 clips)
  • Motion graphics transparent export
  • AI music generation
  • All AI agent editing capabilities

Questions

AI captions FAQ

How does ChatCut generate captions?
ChatCut transcribes your footage on upload into a word-level transcript, then turns that transcript into captions timed to each word. Because they come straight from the transcript, they're accurate on the first pass — edit a word in the transcript and the caption updates with it.
Are the captions word-level and accurate?
Yes. Every word carries its own timestamp, so captions land on the beat instead of drifting a whole line at a time. Fix any word in the editable transcript and the on-screen caption follows it.
What languages do AI captions support?
Captions work in 100+ languages, with the language auto-detected on upload. You can also translate the captions to publish the same clip for a wider audience.
Can I change how the captions look?
Captions are a real track on the timeline. Pick from 20+ styles — clean, karaoke, boxed, pop — and restyle font, size, color, and the highlight word in one click; every caption updates at once.
Is it free, and does it work in the browser?
It's free to start, no card required. ChatCut runs in any modern browser on Mac or Windows with nothing to install, and heavy renders happen in the cloud so your machine isn't tied up.
Can I burn the captions into the video or export a caption file?
Yes. Burn captions into the video on export, or export a timed caption file (SRT/VTT) to use elsewhere. Word-level timing is preserved either way.

Caption your first video

Upload the take, get the transcript, style the captions. Free to start, editable after, all on your timeline.