Convert audio to a Word document

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

A Word document

Word (DOCX), TXT, SRT and VTT, on every plan. In Word, each block of text begins with its time; where the transcript separates speakers, the block carries the speaker's name as you set it. Both can be left out of the export.

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.

Editing before export

Fix names and misheard words in the transcript, with the passage playing, so the document comes out corrected.

A time on every word

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

Summary and translation

Summarise the recording in the shape that fits it, or translate the transcript into another language.

The transcript's text, the speaker names and the block times go into the document — not the audio. The document is yours to format: headings, a title page, the font your institution requires. Where the transcript does not separate speakers, consecutive remarks by different people can come out as a single block with its start time only.

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. Fix them here first: a correction made in Word is not in the transcript, and the next export will not have it.

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.