Import a video
Open KatKut AI and choose Auto Captions & B-Roll. Pick one talking-head video from your gallery. Free accounts can use videos up to 1 minute long; Pro raises that to 5 minutes.
KatKut AI Studio Editor
iPhone & Android
Captions, translation and B-roll for your videos. Automatically.
Studio Editor listens to your video, writes accurate captions in the language you speak, translates them if you want, and cuts in matching stock footage. Review everything in a simple editor, then export a finished vertical video to your phone.
Free to start 69 languages Your video file never leaves your phone
What Studio Editor does
One workflow from raw talking-head clip to finished short
Captions, translation, B-roll and styling that usually take an hour in a timeline editor, done in one pass and left open for you to adjust.
Automatic captions and subtitles
Word-timed captions generated from your speech and kept verbatim in the language you spoke. Ten caption styles, five of them animated word by word.
Translate captions into 69 languages
Choose the spoken language and the caption language separately. Speak Nepali and caption in English, speak English and caption in Spanish, or keep both the same.
Native or Roman script
For languages not written in Latin letters, caption in the native script or a romanised version. The words stay the same; only the letters change.
Smart B-roll, emoji and stickers
AI reads what you are saying and cuts in matching stock footage at the right moments, adds contextual emoji to captions and animated icon overlays. Each one can be switched off.
You stay in control
Every caption and B-roll clip is editable: retime, move, delete, rewrite the text, change the style, undo anything. Nothing is encoded until you tap Export.
Rendered on your phone
Exported by your device's hardware encoder as a 9:16 vertical video that matches your source resolution, saved to your gallery and ready for TikTok, Reels or Shorts.
Spoken and caption languages include
- Nepali (नेपाली)
- Hindi (हिन्दी)
- English
- Bengali (বাংলা)
- Urdu (اردو)
- Tamil
- Telugu
- Marathi
- Indonesian
- Spanish
- Portuguese
- French
- German
- Arabic
- Thai
- Vietnamese
- Japanese
- Korean
- Chinese
- and 50 more
How it works
Five steps, one video
You make three or four choices. Studio Editor does the transcription, the writing and the footage search, then hands the result back to you before anything is rendered.
Choose the spoken language and the caption language
Tell Studio what language is spoken in the video. Turn on Translate captions to caption in a different language, pick native or Roman script where that applies, and optionally type a one-line topic so names and places come out right.
Let AI generate captions and B-roll
Studio transcribes your speech with word-level timing, writes the captions (translated if you asked), and searches for stock footage that matches what you said. Progress is shown stage by stage.
Review and edit in Studio Editor
Watch the result with captions and cutaways playing live. Tap any caption to rewrite it, drag handles to retime it, move or remove a B-roll clip, switch caption templates and colours, and undo anything. The video is not re-encoded while you edit.
Export to your gallery
One tap renders the final video on your phone and saves it to your gallery, with share shortcuts for TikTok, CapCut and Instagram. Add music or a voiceover in your usual app if you want to.
See it in the app
Real screens from KatKut AI on iPhone. Swipe to scroll.
Swipe or scroll →
Also in KatKut AI
Multi-Clip Reel: many clips in, one reel out
Shot a day's worth of short clips? Drop them in and KatKut AI scores every clip for sharpness, exposure, motion and sound, keeps the best moments, and assembles a 9:16 reel in seconds. Eight pacing styles, from Balanced to Snappy to Food & Cooking. Landscape clips get a blurred fill instead of black bars.
The Reel tool runs entirely on your device; no part of your footage is uploaded. Read more about Multi-Clip Reel.
Privacy, stated plainly
What leaves your phone, and what never does
We would rather you know exactly how it works than read a vague promise.
Your video file stays on your phone
Studio never uploads the video itself. It extracts the audio track on-device and sends only that for transcription. Rendering and export happen on your phone.
What Studio does send
The audio track goes to our speech-to-text provider; the resulting text transcript goes to an AI model to write captions and choose B-roll search terms. Neither is stored on our servers.
Multi-Clip Reel is fully on-device
Analysis, selection and export all run locally. Nothing about your clips is sent anywhere.
Read the full privacy policy, including which providers are involved.
Free and Pro
Start free, upgrade when you need more minutes
Pro is a single plan. No tiers to compare.
Free
$0
- 4 minutes of Studio captioning a month
- Each Studio video up to 1 minute long
- All 69 languages, translation and every caption style
- Multi-Clip Reel with all eight styles
- Watermark on exports, ads before and during export
Pro
$3.99/month
- 120 minutes of Studio captioning a month
- Each Studio video up to 5 minutes long
- No watermark on any export
- No ads
- Cancel any time
Try KatKut AI Studio Editor
Free to download. Caption your first video in the language you speak, translate it if you like, and export it to your gallery in minutes.
Requires iOS 16.4 or later on iPhone. Studio needs a free account so your monthly minutes can be tracked.