Skip to content
Scriptorium
Transcribe free

Interviews

Interview transcription

To transcribe an interview, upload the recording, choose the language, and review the transcript, where each speaker is labelled and every line has a timestamp. Rename the speakers, correct the text, and export TXT or Markdown. One file up to 15 minutes and 25 MB is free with no account.

Journalists, researchers, recruiters and podcasters all end up with the same job: a recorded conversation that has to become text. Upload it, get timestamped lines with each speaker labelled, and edit it into the version you need.

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

Key facts

Last updated:

Who said what

In a two-person interview the labelled turns are what makes a transcript usable. Speakers are told apart by the sound of their voices and shown as Speaker 1, Speaker 2 and so on, up to eight; rename them once and the whole transcript updates. Two people with similar voices, or interruptions where both talk at once, are where labels go wrong, so skim those passages.

Quotes need checking against the audio

If you will quote someone, check the exact words against the recording. The timestamp on each line takes you to the right second. Automatic transcription tends to tidy up false starts and may mishear names, so treat it as a fast first draft rather than a verbatim legal record.

Consent and confidentiality

Tell the person they are being recorded and what will happen to the recording. Uploading sends the file to our server; for material that must not leave your own machine, read about self-hosted transcription.

Getting the text out

Export as plain text or Markdown for your article, as timestamped text for your own reference, or as SRT or VTT if the interview is a video you will caption.

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 it separate the interviewer from the guest?
Yes, when the voices are distinct enough. It labels up to eight speakers and you rename them.
Does it work on phone interviews?
Yes. Phone audio is narrowband and transcribes a little less well than a recording made in a quiet room.
Is it suitable for research interviews?
As a first draft, yes. Correct it against the audio before you analyse or quote it. No accuracy figure is promised.
Is it free?
Yes — one interview 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.
Is it good enough for quotes?
Treat the transcript as a draft. Check every quote against the audio before publishing.
How should I record an interview?
Use a separate microphone near each speaker if you can, in a quiet room.
Can it remove filler words?
No. It transcribes what was said; edit the lines you want cleaned.
Can I transcribe a phone interview?
Yes, if you have the audio file; phone-line quality may need more checking.

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.

Transcribe free — no sign-up Create free account