Import one video of you talking. Studio transcribes what you said, writes word-timed captions in that language or translates them into another, and adds B-roll footage, motion graphics, sound effects, transitions and an opening hook, all automatically. Change anything you like, then export a vertical 9:16 or widescreen 16:9 video to your phone.
Used by 5,000+ creators around the world
Free to start 101 spoken, 140 caption languages 9:16 and 16:9 Video file never uploaded
Everything below is in the app today, on iPhone and Android. Every automatic result can be edited afterwards, and the visual extras can be switched off for captions only.
Studio transcribes your speech with word-level timestamps and turns it into short, readable captions. The text is kept verbatim in the language you spoke; nothing is paraphrased or summarised. Only words the transcriber flagged as uncertain are offered for repair.
Captions come in trending, eye-catching styles, many animated word by word, and are burned into the exported video, so they show on every platform and for viewers watching on mute.
Tell Studio which of 101 languages is spoken in the video so transcription is accurate. English sits in the same list as Japanese, Turkish, Hindi, Arabic and the rest, all treated equally.
Turn on Translate captions and choose a caption language that differs from the spoken one. Speak Turkish and caption in English, speak Hindi and caption in Arabic, speak English and caption in Japanese. Any of the 101 spoken languages can be the source, and any of 140 the target. More on caption translation.
For languages not written in Latin letters, choose whether captions appear in the native script or a romanised version, for example नमस्ते or namaste, or こんにちは or konnichiwa. Romanising keeps your exact words and changes only the letters, which suits creators whose audience reads the language but types it in Latin letters.
With Smart B-Roll on, an AI model reads the transcript, works out what each moment is about, and searches licensed stock footage for a matching clip. Each cutaway starts on the word it shows, is kept short, and is balanced so the focus stays on you. The voice continues underneath every cutaway.
Footage is searched in the shape of your video: portrait clips for a 9:16 video, landscape first for a 16:9 one. Smart B-Roll is the one switch for the extras: footage, stickers, motion graphics, sound effects, transitions and the opening hook. Switch it on in setup, or leave it off for captions only.
Our AI reads the whole video, finds the moments worth showing and adds animated graphics for them, timed to your words and laid out for 9:16 or 16:9, so your video comes back more engaging. You can still change a graphic's words and numbers. More on motion graphics.
The first seconds decide whether people keep watching. The AI reads what you say at the start and writes a short, attention-grabbing hook from it, animated over the opening. Change the words, the look, the colour or the font, or delete it.
Cutaways slide or flash in with smooth transitions, and graphics, stickers and cutaways get sound effects that match what happens on screen, all timed automatically, while your voice keeps playing throughout.
A vertical video is exported 9:16, for TikTok, Reels, Shorts and Facebook Reels. A horizontal or square video gets a choice on the setup screen: 9:16, or 16:9 for YouTube, Facebook and LinkedIn (16:9 is preselected for horizontal video, 9:16 for square).
A video in a different shape from the frame, such as a 4:5 clip, a square one, or a horizontal one in 9:16, is shown in full and centred. You choose what fills the space around it: a blurred copy of your video, or black. Captions, graphics, the hook and B-roll all follow the format you chose.
The AI may add an emoji to a caption where it fits. It is part of the caption text, so you change or remove it by editing the caption. Smart B-Roll can also place an animated sticker with a light sound at a key moment, which you can move or delete like any clip.
Type a one-line summary such as "travel vlog in Lisbon" or "gym workout tips". It helps the AI spell names and places correctly and pick relevant footage. Your own words always come first: the topic only helps with names, spellings and footage.
The editor shows a live preview above a timeline with three tracks: overlays (B-roll, stickers, graphics and the hook), your footage, and captions. Tap a caption to rewrite it and drag its handles to retime it. Move, trim or delete a cutaway. Select a graphic or the hook to change its words. Switch the caption style, colour, font, position and size. Every change can be undone, and nothing is re-encoded until you export.
Export renders once, on your phone, using the hardware encoder. The output is a 9:16 or 16:9 video at the resolution of your source (1080p, 1440p or 4K where your device supports it), saved to your gallery with share buttons that open your phone's share sheet, for TikTok, Instagram, YouTube, Facebook, LinkedIn or CapCut.
Five steps. The AI does the transcription, the writing, the footage search and the graphics; you make the choices and the final call.
On the home screen, tap Select 1 video and choose one video from your gallery. Studio is built for a single talking-head clip: you speaking to the camera.
Under Language, set Spoken in to the language of the video. Under AI enhancements, switch on what you want:
Studio extracts the audio on your phone, transcribes it with word-level timing, writes the captions (translated if you asked), and adds B-roll footage, motion graphics, sound effects, transitions and the opening hook. A stage-by-stage progress bar shows what is happening. If the AI planning step fails for any reason, you still get a captioned video from the transcript.
The finished short plays first. Tap Edit to open the editor if you want changes.
Tap Export. The video renders once on your phone, 9:16 or 16:9, and is saved to your gallery, with share buttons for TikTok, Instagram, YouTube, Facebook, LinkedIn or CapCut. Free exports carry a small watermark; exports on a paid plan do not. Your project is kept as a draft so you can come back and re-export.
Languages in the first group can be spoken in the video and captioned; the second group can be chosen as a caption or translation language. Languages marked with their native name also offer a Roman-script option.
Spoken and caption languages (101)
Caption and translation languages (39 more)
If your video is you speaking, Studio removes most of the editing that stands between recording and posting.
Post captioned TikToks, Reels and Shorts in minutes. Captions, B-roll, graphics and a hook in one pass.
Shoot horizontally and export 16:9 for a YouTube video, a Facebook post or LinkedIn, with captions, B-roll and graphics laid out for the wide frame.
Turn a piece-to-camera into a proper edit: cutaways where you describe something, captions that keep viewers watching on mute.
Describe a place and get matching footage and graphics, automatically. Caption in your language, or translate for an international audience.
Accurate, verbatim captions for lessons, tutorials and tips. Automatic graphics make each point easier to follow.
Speak Spanish, Japanese, Turkish, Hindi, Arabic or any of 101 languages and reach viewers who read another. Native or Roman script, your choice.
Made for everyone: import, pick a language, generate, export. Fine-tune in the editor whenever you like.
Studio is designed so the automatic result is usually right, and every part of it is yours to override.
| Element | Done automatically | Editable in the editor |
|---|---|---|
| Transcript | Word-level transcription in the selected spoken language | Rewrite any caption's text |
| Caption timing | Captions cut at natural phrase boundaries, aligned to the words | Drag handles to retime; move or delete |
| Caption language | Verbatim by default; translated when you choose a different caption language | Set in setup; edit individual translated lines afterwards |
| Script | Native script by default for non-Latin languages | Switch on Romanised captions in setup |
| B-roll | Stock footage matched to meaning, placed and trimmed to fit | Move, trim the start or end, or remove any clip; turn the feature off |
| Motion graphics | Added by AI where they make a point clearer, timed to your words | Change the words and numbers; move or delete; Smart B-Roll off removes them |
| Opening hook | Up to six words written from your first seconds, animated in a design that suits it | Change the words, design, colour and font, or delete it |
| Emoji and stickers | An emoji in a caption where it fits; animated stickers at key moments | Edit the caption to change or remove an emoji; move or delete a sticker |
| Caption style | Plain white text (the None style) | Choose another style; set colour, font, position and size |
| Sound effects and transitions | Transitions into cutaways and matching sound effects, timed automatically | Move or delete any cutaway, graphic or sticker, and its sound goes with it |
| Format | 9:16 for a vertical video; 16:9 preselected for a horizontal one, 9:16 for a square one | Choose 9:16 or 16:9, and Blur or Black around a video that does not fill the frame, in setup |
| Export | 9:16 or 16:9 at source resolution, hardware-encoded on your phone | Re-export any time from the saved draft |
Works with the apps you already use. Share the finished video to CapCut, TikTok or Instagram to add music or a voiceover, and use Multi-Clip Reel to turn many clips into one reel.
Real screens from the app. Swipe to scroll.
Swipe or scroll →
Studio is the AI video editing tool inside the KatKut AI app for iPhone and Android. You import one talking-head video and choose the spoken language and the caption language. Studio generates word-timed captions, optional translation, matching stock B-roll, motion graphics and an opening hook. You can edit every part in a timeline editor, then export a vertical 9:16 or widescreen 16:9 video to your gallery.
Studio extracts the audio from your video on your phone and sends only that audio to a speech-to-text service, which returns a transcript with a timestamp for every word. An AI model then splits the transcript into captions and, if Smart B-Roll is on, chooses the moments for stock footage, motion graphics, sound effects and transitions, and writes the opening hook. Short search terms are used to find licensed stock footage in the shape of your video, which is downloaded to your phone, and the graphics are drawn by the app. The app checks every caption and cutaway for timing and overlap, then shows you the result before anything is rendered.
Open KatKut AI, tap Select 1 video, pick a video, set the spoken language, and tap Generate. Captions are created automatically and burned into the video when you export. You can change the caption style, colour, font, size and position in the editor before exporting.
On the Studio setup screen, tap Spoken in and choose from the list of 101 languages. You can search the list by name. The language you pick is passed to the transcriber, so choosing the right one is what makes the captions accurate.
On the setup screen, switch on Translate captions and choose a Translate to language. The spoken language and the caption language are set independently, so any of the 101 spoken languages can be the source and any of the 140 caption languages the target. Translated captions can still be edited line by line in the editor.
Yes. For languages not written in Latin letters, such as Hindi, Japanese, Arabic or Nepali, captions use the native script, or switch on Romanised captions on the setup screen for Roman letters. Romanising keeps your exact words and changes only the letters, so नमस्ते becomes namaste. Choosing a different caption language translates instead.
With Smart B-Roll turned on, the AI reads the meaning of what you said and searches for licensed stock footage that illustrates it, for example footage of a street market when you talk about one. Each clip starts on the word it illustrates, is kept short, and is balanced so the focus stays on you. Footage is searched in the shape of your video: portrait for 9:16, landscape first for 16:9. Your voice continues under every cutaway. You can move, trim or remove any clip in the editor, or turn the feature off entirely.
Automatically. Our AI reads the whole video, finds the moments worth showing and adds animated graphics for them, timed to your words and laid out for 9:16 or 16:9. You can change a graphic's words and numbers, move it or delete it. Graphics are added whenever Smart B-Roll is on.
A hook is the short line on screen in the first seconds that tells viewers why to keep watching. Studio writes one automatically, up to six words taken from what you say near the start of your video, and animates it over the opening to help your video reach more people. You can rewrite it, change its look, colour or font, or delete it. Studio writes a hook only when Smart B-Roll is on and your opening gives it something specific to say.
Yes. Leave Smart B-Roll off on the setup screen and Studio adds captions only: no stock footage, stickers, motion graphics or hook. Translation, Roman script and every caption style still work.
Yes, automatically. With Smart B-Roll on, cutaways slide or flash in with smooth transitions, and graphics, stickers and cutaways get sound effects that match what happens on screen, all timed for you. Your voice keeps playing throughout, and you can move or delete any clip in the editor.
Yes. The editor has a live preview and a timeline with three tracks: overlays (B-roll, stickers, graphics and the hook), your footage and captions. Tap a caption to rewrite its text, drag its handles to change when it appears, or delete it. Drag a B-roll clip to move it, trim its start or end, or remove it. Select a graphic or the hook to change its words. Switch the caption style and set the text colour, font, position and size. Undo and redo cover every change. Nothing is re-encoded while you edit; the video is rendered once, when you tap Export.
Tap Export in the editor or on the result screen. The video is rendered on your phone using the hardware encoder and saved to your device gallery as a 9:16 or 16:9 video at your source resolution. Share buttons appear when it finishes and open your phone's share sheet, for TikTok, Instagram, YouTube, Facebook, LinkedIn or CapCut. Free exports include a watermark; exports on a paid plan do not.
Yes. When you pick a horizontal or square video, the setup screen asks for the format: 9:16 for TikTok, Instagram Reels, YouTube Shorts and Facebook Reels, or 16:9 for YouTube, Facebook and LinkedIn. 16:9 is preselected for a horizontal video and 9:16 for a square one; a vertical video is always exported 9:16. Captions, motion graphics, the hook and B-roll are laid out for the format you choose, and a 16:9 export is 1920×1080, or 1440p or 4K when your source and phone support it.
It is shown in full and centred. When its shape differs from the frame you chose, for example a square or 4:5 video, or a horizontal video in 9:16, the setup screen asks what fills the space around it: Blur, a soft blurred copy of your own video, or Black, classic black bars.
On the free plan, Studio captions up to 4 minutes of video per month, up to 2 of them AI-enhanced (translation, romanised captions or Smart B-Roll), each video up to 1 minute long, with a watermark on exports and ads before and during export. Every feature is included: all languages, translation, B-roll, motion graphics, hooks and caption styles. Paid plans raise the allowance and remove the watermark and ads: Pro costs $3.99 per month for 60 minutes (20 AI-enhanced) and videos up to 2 minutes; Pro Plus costs $6.99 for 150 minutes (40 AI-enhanced) and Pro Max $9.99 for 300 minutes (80 AI-enhanced), both with videos up to 5 minutes. The local price may vary on the App Store. Plans are purchased from Settings in the app: through Apple's in-app purchase on iPhone, and through a secure Stripe checkout on Android.
Your video file is never uploaded. Studio extracts the audio track on your phone and sends only that audio to a transcription provider. The text transcript, plus the optional topic you typed, is sent to an AI model to write captions and choose B-roll search terms. Search terms alone are sent to the stock footage providers. Neither the audio nor the transcript is stored on our servers. Rendering and export happen entirely on your phone. The full list of providers is in the privacy policy.
One clip of a person speaking to the camera, recorded in a reasonably quiet place, in a single language. Studio takes exactly one video per project. If you have many short clips rather than one, use the Multi-Clip Reel tool instead.
Studio keeps your original voice and adds captions, B-roll, graphics, a hook, sound effects and transitions. To add music or a voiceover, use the share buttons on the export screen to open the finished video in CapCut, TikTok or Instagram and add it there.
More general questions about the app, accounts and billing are answered on the About page.
Download KatKut AI, pick a video of yourself talking, and get captions, B-roll, graphics and a hook in the language you speak. Free on iPhone and Android.
Used by 5,000+ creators around the world
Requires iOS 16.4 or later on iPhone. Studio needs a free account.