Skip to content

For journalists

Transcribe interviews for journalists

Upload an interview recording, get timestamped text with speakers labelled, and find the quote you need fast. It is a draft you review: every quote you publish should be checked against the audio, and some sources should never be uploaded at all.

Free preview: one file up to 15 minutes and 25 MB, 3 tries a day, no account needed.

Want to keep your transcripts? Create a free account

Speed is the benefit; the audio is the record

Typing out an hour of interview takes much longer than the hour. A first draft in minutes lets you scan for the passages that matter and jump to them by timestamp. But the transcript can tidy false starts, drop a hedge such as 'I think', or mishear a name, and any of those can change what someone seems to have said. Your published quote must come from the recording, not from the draft.

Verifying a quote

  1. Find the passage in the transcript with search or by reading.
  2. Click or note the timestamp and play that second of audio.
  3. Correct the line in the editor so the text now matches what was said.
  4. Check names, titles, numbers and place names separately, and against another source where you can.

Sources, consent and what leaves your machine

Tell the interviewee they are recorded and what will happen to the recording; recording rules differ by place, so check yours. Uploading sends the audio to our server. If a source's safety, a legal duty or a newsroom policy means the recording must not sit on anyone else's server, do not upload it. Look at self-hosted transcription for running it on your own hardware, and at this guide to keeping recordings private. For sources who need anonymity, a cloud service is the wrong place for the audio.

Drafts you review

Treat the transcript as a working draft. We give no accuracy figure, and a transcript from this site is not a verbatim legal record. Overlapping voices, phone-line audio and strong background noise are where words go missing, and speaker labels (up to eight, with a free account) can swap two similar voices.

Getting the text out

Export plain text or Markdown for your notes and draft, timestamped text for your own reference, or SRT and VTT if the interview is video you will caption. Without an account one file can be up to 15 minutes and 25 MB. A free account lifts those per-file limits and keeps your transcripts in a library you can search, so for a full-length recording create one instead of cutting the file up.

How it works

  1. Add a recording

    Drop in a video or audio file, choose one from your device, or record from the microphone. Nothing to install.

  2. It transcribes

    Speech becomes timestamped text, with speaker labels when more than one person talks.

  3. Read, fix, export

    Click any line to correct it, then download TXT, subtitles, Markdown, JSON or CSV.

Questions

Can I use the transcript as the quote?
Only after checking it against the audio. Treat it as a draft.
Is it safe for a confidential source?
Not if the recording must stay off third-party servers. Use self-hosting or transcribe by hand.
Does it label who is speaking?
Yes, with a free account, for up to eight speakers, and you rename them. Check overlaps.
Can it transcribe a phone-call recording?
Yes, if you have the audio file and you were allowed to record the call. Phone audio is rougher.
Is it free?
Yes — one recording up to 15 minutes and 25 MB with no account, up to 3 tries a day. A free account keeps your transcripts in a library and lifts the guest limits; the current limits and paid plans are on the pricing page.

Want your transcripts saved and longer files? Create a free account · See pricing · All use cases

Try it with your file

No account needed for a first transcript.