How much does it cost to summarise a recording?

To try it, nothing: without an account, the trial transcribes up to the first 10 minutes of a recording, and the result page shows what you can read without paying and how to read the rest. What the free account includes today and Pro's prices are on the pricing page.

Can I choose what kind of summary I get?

Yes. The kind is picked from the transcript — meeting, interview, lecture or talk, sales call, user research or conversation — and you can pick another, which makes a new summary with that kind's sections.

Does the summary say who said what?

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. The meeting summary attributes points to speakers where the transcript makes that clear.

Which files can I summarise?

Any recording we transcribe: we accept MP3, M4A, WAV, OGG, Opus, MP4, MOV and WebM, among others.

What happens to the recordings I upload?

Your recordings and transcripts are not used to train models. In the no-account trial, the file and the transcript are deleted 48 hours later — or 7 days after payment, if you buy just that transcript; in an account, they are kept until you delete them.

Summarise an audio or video recording

Upload the recording and try the transcript here, with no account. In an account, the transcript comes with a summary in the shape that fits the recording — a meeting, an interview, a lecture, a sales call, a research session or a conversation — and with a time on every word of the transcript, so a point in the summary can be checked against what was said.

LanguageIdentify speakers

Auto detect can mishandle a recording that switches language.

Free: one recording up to 10 minutes · its transcript to read · no account · deleted after 48 hours

What you get

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

A summary in the recording's shape: The kind of recording is picked from the transcript, and you can change it; picking another kind makes a new summary with that kind's sections, below.
A meeting: The discussion in order; only the decisions actually settled; the open questions and disagreements left standing, not smoothed over; and action items with who took them on, where the recording makes that clear.
An interview: The recurring themes; notable quotes in the speaker's own words, quoted exactly, grammar untidied; and the factual claims a reader might want to check.
A lecture or talk: The key concepts, the definitions given, the examples and analogies used, and the questions asked with how they were answered.
A sales call, user research, or a conversation: A sales call: the prospect's stated needs in their framing, the objections, anything said about budget and timing, and action items. User research: pain points in the participant's own terms, what they actually do as distinct from what they say they want, verbatims exactly as said, requests recorded as requests. Anything else: the key points and the moments worth returning to.
Export: Word (DOCX), TXT, SRT and VTT, on every plan.

What a summary can and cannot do

A summary is made from the automatic transcript, so a name misheard in the transcript is misheard in the summary. 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. The summary does not point to times; to find where something was said, ask a question about the recording — the answer points to the passages and the moment they are in.

A summary is not a record. The meeting shape lists only settled decisions and refuses to smooth over open questions on purpose: what it leaves out is a signal, not a gap. Read the transcript for anything you will act on.

Long recordings

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.

Before you upload

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.

Frequently asked questions

How much does it cost to summarise a recording?: To try it, nothing: without an account, the trial transcribes up to the first 10 minutes of a recording, and the result page shows what you can read without paying and how to read the rest. What the free account includes today and Pro's prices are on the pricing page.
Can I choose what kind of summary I get?: Yes. The kind is picked from the transcript — meeting, interview, lecture or talk, sales call, user research or conversation — and you can pick another, which makes a new summary with that kind's sections.
Does the summary say who said what?: 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. The meeting summary attributes points to speakers where the transcript makes that clear.
Which files can I summarise?: Any recording we transcribe: we accept MP3, M4A, WAV, OGG, Opus, MP4, MOV and WebM, among others.
What happens to the recordings I upload?: Your recordings and transcripts are not used to train models. In the no-account trial, the file and the transcript are deleted 48 hours later — or 7 days after payment, if you buy just that transcript; in an account, they are kept until you delete them.