Transcribe training videos

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

The narration as text, with the time

Click any line to hear that passage; the transcript follows the video while it plays.

Captions

Word (DOCX), TXT, SRT and VTT, on every plan. SRT or VTT for your video platform or learning system — or burn the captions into the video and download the finished file, on every plan, Free included.

A handout

Export to Word and you have a text version learners can search and print.

Translation

Translate the transcript for staff who work in another language, and have a speaker of it read the result beside the original.

A summary built for a lesson

The key concepts, the definitions given, the demonstrations used and the questions asked, if any were.

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.

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 training video that is your own vocabulary: product names, internal acronyms, the names of systems and the steps read off a screen. Fix each where it sits before you export the captions, and every caption carries the fix.

Only the narration is transcribed. Text on the slides, the menu labels you click through in a demo and anything in the video's own captions are not read — say it aloud in the recording if learners need it in the text. Background music under the narration adds errors; a version without it carries fewer of them.

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.