Captions for Instagram, TikTok and YouTube Shorts

In an account — free or Pro, with the same features — the transcript comes with:

Captions burned into the video

The finished video, with the captions in the picture, ready to download and post — on every plan, Free included. Fix the text before you render: the captions are fixed when the render is asked for, so a later edit goes into the next render.

The words first, with a time on every word

Click any line to hear it; the captions follow the word times, so a caption appears when the words are spoken.

Editing in the text itself

Names, slang, the product you are talking about: fix them where they sit, before you render.

Subtitle files instead

Word (DOCX), TXT, SRT and VTT, on every plan — SRT or VTT if your editor or platform takes a caption file rather than captions in the picture.

Who spoke

In American English, British English and Indian English, the transcript separates the voices into Speaker 1, Speaker 2 and so on; you rename each label once, and the name holds for the whole transcript. In Australian English and Philippine English, it separates them too, on recordings of up to 2 hours. If the separation fails, the transcript comes without speaker labels, and says so.

A short clip is short: in the no-account trial, you can read everything it transcribes, and the result page says what you are seeing. Music and sound effects are not captioned, and text already in the picture is not read — only speech becomes captions. Every automatic transcript has errors, and they cluster on proper names, numbers and technical terms. Before you quote a passage, click the line and listen: with a time on every word, that check takes seconds. In a short clip that is the name or product you say once, which the whole caption hangs on.

Where several people talk over each other in the clip, the captions need review before you render. Hold the phone close when you film, and the text comes back with fewer errors.

Without an account, the trial transcribes up to the first 10 minutes of a recording. On Pro, each file can be up to 8 hours, within the month's included hours; what each plan includes, the pricing page shows. See plans and prices.

On long recordings, speaker labels can wander from one section to the next — a consequence of how long audio is processed, not a setting.

Name the main language rather than leaving it on automatic. Automatic detection has to decide what language each stretch of speech is in, and where a recording switches language, what was said in the other one may come back translated instead of transcribed — or not come back at all. Either way nothing is marked as missing: the transcript will look complete.

Philippine English is marked “preview” in the language list: offered, but without a quality commitment yet, so check its transcript more closely before you use it.