Which language do I choose when uploading?

The language spoken in the recording. The translation into the language you want to read comes afterwards, in an account.

How much does it cost?

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.

Does the transcript say who is speaking?

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.

Which files can I upload?

Audio or video as it is: 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.

Translate a recording into another language

Upload the recording and pick the language that is spoken in it — not the language you want to read. Try the transcript here, with no account. In an account, the transcript is then translated into another language, and you read the translation beside the original, with a time on every word of the original to hear what was actually 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:

The transcript in the spoken language: Made first, with a time on every word: click any line to hear that passage.
A translation of the transcript: Into another language, as a text of its own, read beside the original.
Editing before translating: Fix names, places and misheard words in the original first — a translation carries every error it is given.
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 and questions: Summarise the recording and ask questions about it; the answers point to the moment in the recording.
Export: Word (DOCX), TXT, SRT and VTT, on every plan.

What translating a recording involves

The translation is of the transcript, not of the sound: it is as good as the transcript under it. 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 those in the original before you translate, and have someone who reads the other language check what the translation did with them.

Transcription works in 82 languages, and the choice that matters most is naming the language spoken in the recording. A recording that switches between languages is the case to read about below before you upload.

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

Which language do I choose when uploading?: The language spoken in the recording. The translation into the language you want to read comes afterwards, in an account.
How much does it cost?: 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.
Does the transcript say who is speaking?: 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.
Which files can I upload?: Audio or video as it is: 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.