Transcription runs on the phone
Burnin does not send your video anywhere. Apple's on-device speech transcriber turns speech into text right on the iPhone, which is why captioning keeps working on a flight, underground, or with the data switched off.
Grouped the way a video happens: import it, transcribe it, edit it, export it. Everything on this page works with no account.
Burnin does not send your video anywhere. Apple's on-device speech transcriber turns speech into text right on the iPhone, which is why captioning keeps working on a flight, underground, or with the data switched off.
The first time you transcribe in a language, its model downloads. After that it stays on the phone, and every video in that language transcribes with no connection at all.
Burnin doesn't fetch any other model. Segmentation, gap retries, editing and export all use what's already on the phone.
Burnin detects which language is being spoken on its own. A manual picker is there for when you would rather choose, or when a video mixes languages in a way detection cannot resolve on its own.
A raw transcript is automatically segmented into caption-length lines, so what appears on screen reads at a glance instead of running on as one long sentence.
Burnin looks for stretches of five seconds or more with no caption, where speech likely got dropped. It transcribes just that stretch a second time, folds any words it finds back into your captions, and leaves a stretch that's really silent empty.
Burnin captions everyone who speaks, in the order they speak. It doesn't label who's talking, so if a conversation needs names or a dash at each new voice, you add them in the editor.
Segmentation and gap detection need no network signal at all, and a gap retry uses the same on-device transcriber and language pack as the first pass.
Tap a caption, or the add button floating over the list, to open a large editor sheet at full height from the first frame, with its own delete control and a "Done" to close it.
Add a caption and it is inserted at the video's current position, in chronological order alongside its neighbors, not always tacked onto the end of the list.
Each caption's start and end time is a handle on a timeline strip. Drag either edge to retime it against the video underneath, with a margin above and below every block so there is always room to start a pan.
Drag the playhead on the timeline to scrub the video directly, instead of only watching it play. Hold it near either edge and the timeline scrolls along, so the playhead stays on screen even in a longer video.
Dragging one caption's edge past its neighbor is not allowed. Captions cannot be made to overlap by accident.
Every text edit and every trim is on the undo stack, twenty to thirty steps back, so an experiment you don't like is one gesture from gone.
Edits are saved automatically roughly every 600ms as you make them. Closing the app mid-edit, or a call coming in, does not cost you the work.
The video preview shows exactly what the exported file will look like, captions and all, updated as you edit.
Right after export, before the share sheet opens, Burnin offers a title and a short description with a couple of hashtags, generated from the captions you just edited, not re-transcribed from scratch.
Neutral, balanced, or clickbait. Switching tone regenerates the title and description to match, and you can skip the screen entirely and export with just the video.
Generation runs through Apple's on-device Foundation Models when available, so the transcript never leaves the phone to be summarized.
On a device without Apple Intelligence, or if generation fails, an on-device heuristic takes over: it picks a named person, place, or organization from the transcript for the title, and the single most information-dense sentence for the description, never just the first line.
Original, 9:16 for Reels, TikTok and Shorts, 1:1 for square feed posts, or 16:9 widescreen. Pick the shape the destination actually wants.
720p, 1080p or 4K, with captions burned directly into the exported video rather than added as a separate track.
The video export is a single file with the captions part of the picture, so it plays correctly anywhere without a subtitle track attached. If you need the captions as text too, the SRT button in the editor exports them as an .srt file you can share.
When a transcription or an export finishes, Burnin lets you know with a notification, so you don't have to keep checking. It comes from the phone itself, not a server, and only if you've allowed notifications.
Import a video and it becomes a project in your library, with its captions and edits kept alongside it.
Every project in the Library shows whether it's still a Draft or already Exported, with the video's length on the date line beside it.
Rename a project to find it later, delete one you no longer need, or select several at once to clean up in bulk.
If the original video file goes missing locally, Burnin can recover it from your Photos library instead of leaving the project broken.
Projects are stored locally, on-device. There is no cloud sync and no account for them to belong to.
Most caption apps run in the cloud because that is the easier engineering path, not because your video needs it to. Burnin does the same job the other way around.
| Comparison | A typical cloud captioning app | Burnin |
|---|---|---|
| Where your video goes | Uploaded to a server to be transcribed | Stays on your phone, transcribed on-device |
| Account | Sign-up required to export | None, ever |
| Internet connection | Needed every time you transcribe or export | Only once, to download a language model |
| Price | Often a subscription for full-length or HD export | No subscription, no ads |
A video shot for one place rarely fits another. Burnin crops and exports for the shape a platform actually wants, with captions burned in to match.
The source video's own aspect ratio, no crop applied.
Full-height vertical crop for short-form video.
A square crop for feed posts.
Standard landscape, for everywhere else.
Higher resolution means a bigger file and a longer export, and Burnin shows you that trade before you commit to it rather than after the export has already started.
Importing, transcribing, editing and exporting all happen on your phone, and every project stays there. There is no sign-in, so there is nothing to sync and nowhere for a video to go but your own device.
| Importing a video | Nothing. The video is read from Photos or Files and stays on the phone. |
| Downloading a language pack | A request for that language's model file only. No account, no identifier. |
| Retrying a dropped stretch | Nothing. The stretch is transcribed again on the phone, with the language pack that's already there. |
| Transcribing, editing | Nothing. All of it runs on the phone. |
| Exporting a video | Nothing. The captioned file is written to your phone. |
On-device transcription needs a fairly recent Neural Engine, so Burnin supports iPhone 12 and later. Older devices, and the Simulator, are not supported. Burnin runs on iPhone and iPad, though the app is not iPad-optimized yet. An older iPhone can still open a project to write captions by hand or bring in a ready-made subtitle file; it just can't transcribe speech itself.
Sending video to a server would mean an account, a connection, and someone else's copy of your footage sitting somewhere. Running transcription on the phone means none of that has to exist. It costs a one-time model download and it means the oldest supported iPhones do the work themselves rather than a cloud doing it for them.
| Platform | iPhone and iPad (not iPad-optimized yet), iOS 26.0 or later |
|---|---|
| On-device transcription | iPhone 12 and later. Older devices, and the Simulator, are not supported |
| Video formats | MP4, MOV |
| Max video length | No set limit. A longer video takes longer to transcribe and export |
| Account | None. Not required, not offered |
| Price | No ads, no subscription |
Automatic transcription is not perfect on any device, on any app. Burnin's editor exists because every caption is meant to be checked, not accepted blindly, and gap detection is a heuristic that reduces missed speech rather than a guarantee that none is ever missed.
For iPhone, on the App Store. No account needed to use it.