Speech to text: record or upload

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

Punctuated text, with a time on every word

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

Editing in the text itself

Fix a word where it sits, with the audio playing beside it.

Export

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

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.

Summary, translation and questions

Summarise what you said, translate the transcript into another language, or ask where you said something; the answer points to the moment in the recording.

You can also record in the browser, on a phone or a computer. Keep the page open and the screen on until you stop: a browser can end a recording when the page goes into the background.

Speak as you would to a person, not to a machine: the punctuation comes from how you speak, and there are no spoken commands — say “full stop” and you may get the words rather than the mark. Dictating a list or an address? Numbers and names are where errors cluster. 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.

Transcription works in 82 languages. Pick the language you will speak before you start; the limit for recordings that switch between languages is stated below.

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.