Transcribe long recordings

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

The whole recording, with a time on every word

Click any line to hear that passage, however deep in the file it is; the transcript follows the audio while it plays.

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.

Questions instead of scrolling

Ask where a topic came up; the answer points to the passages and the moment in the recording they are in. In a very long recording, a question may not reach the whole of it — when that happens, the answer says how much of the middle went unread.

A summary in the recording's shape

A long meeting gets the discussion, the settled decisions and the open questions; a long talk gets the concepts, the definitions and the examples.

Export

Word (DOCX), TXT, SRT and VTT, on every plan.

Length changes little in the words: the errors are the same ones, on names, numbers and terms, only more of them. 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. What length does change is the speaker labels, stated below, and the upload: a video file of several hours is large, and the audio alone, if you can export it, uploads in a fraction of the time and transcribes the same.

Trim what you do not need before uploading — the setup before a workshop starts is counted against your plan's minutes like everything else.

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.