Generate subtitles for a video

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

Subtitle files

Word (DOCX), TXT, SRT and VTT, on every plan. SRT is what most video editors and players load; VTT is what web video players use.

A time on every word

Cues are cut from the word times, so a subtitle appears when the words are spoken. Click any line to hear it and check.

Editing before export

Fix a name or a misheard word in the transcript and every export after it carries the fix. Edit the text here rather than in the subtitle file.

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.

Captions in the picture, as an alternative

For a short video that goes out on social networks, burn the captions into the video instead — the captions for short videos page explains.

A subtitle is read, not heard: a filler that is harmless in speech is noise on screen. Cut fillers and false starts from the text before you export, and the cues carry the cleaner text. 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. A misspelt name in a subtitle is on screen for every viewer, so fix it in the transcript first.

Only speech becomes subtitles. Music, sound effects and text already on the screen are not described, and where people speak at once, the cue needs review. A video in another language is transcribed in that language — pick it before you upload — and the transcript can be translated in an account.

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.