Transcribe an oral history interview

Upload the recording — a session recorded last week, or a cassette you had digitised — and try it here, with no account. In an account, the transcript comes with a time on every word, so the name of a village or a relative can be heard before it is written down for good, and exports to Word for the archive or the family.

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:

    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.
    A time on every word
    Click any line to hear that passage; the transcript follows the audio while it plays. A time on a story is how a future reader finds the voice telling it.
    Editing in the text itself
    Names of people and places, dates, dialect words — fix them where they sit, with the voice playing.
    A summary that keeps the quotes
    Themes, notable quotes in the speaker's own words — quoted exactly, grammar untidied — and the factual claims a reader might want to check against other sources.
    Translation
    Translate the transcript for family who do not speak the language it was told in, and read it beside the original.
    Export
    Word (DOCX), TXT, SRT and VTT, on every plan — Word for the archive copy, TXT for the catalogue.

    Old voices, old tapes

    A digitised cassette carries hiss, a recorder set too close or too far, and a speaker who never spoke for a microphone before; the transcript carries all of it as errors. 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. Names of people and places are what an oral history is for, so listen to each before it goes in the archive.

    Some archives ask for a literal transcript, with every pause and repetition; an automatic transcript does not promise them — it writes what it hears as words and may drop an “um” or a repeated phrase. Whether the person recorded agreed to the recording being transcribed and kept is yours to settle, as with a typist.

    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.

    Long sessions

    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 transcribe an oral history interview?
    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 it work on an old, noisy recording?
    It transcribes what it can hear, and a noisy tape produces more errors than a clear recording — on names and places most of all. Upload the best copy you have and check each name against the voice before you write it down.
    Does it separate the interviewer from the narrator?
    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?
    The digitised recording as it is, audio or video: 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.