Library

Transcribe an interview: from audio to text, free

Upload a recorded interview and get it back as text, free and with no sign-up. A recording can run up to 120 minutes and the file can be up to 2 GB. Every phrase has a timestamp, and you download Word (DOCX), TXT, SRT or VTT. The file is deleted from our server after 24 hours.

Updated

mp3, m4a, wav, ogg, mp4, mov. Up to 120 minutes and 500 MB; over 95 MB, the sound is compressed in your browser first.

Audio to text

Standard, free

Recordings up to 120 minutes, no sign-up.

What Wovea Plus can do €4.99 a month

Audio to text

Turns a voice message, call or lecture into text with timestamps.

  • Recordings up to 2 hours
  • Timestamps for each phrase
  • Language detected automatically
FreeNo sign-upYour result is saved to the libraryYour file is deleted after 24 hours

How it works

Drop a recording

A voice message, an interview, a lecture or a video.

Speech turns into text

The language is detected automatically, and every phrase gets its own timestamp.

Grab the text

Copy it or download a .txt, .srt or .vtt. You can translate it right away.

Quick facts

PriceFree
Sign-upNot needed
LimitAudio and video up to 2 GB and 120 minutes; the browser takes the sound out of a big file
InputMP3, M4A, WAV, OGG, OPUS, FLAC, AAC, AMR, MP4, MOV, WebM, MKV, AVI, 3GP
OutputTXT, DOCX, SRT, VTT
Where it runsOn our server, from a video only the sound is sent
StorageDeleted from the server after 24 hours
LanguagesDetected automatically
TimeAbout 31 seconds for a 10-minute recording, plus upload
AI tasksUp to 60 per hour from one connection
Key points from the recordingMeeting summary with decisions, tasks and deadlines, lecture notes, the gist of a voice message and a draft reply; the kind of recording is detected automatically, the breakdown exports to PDF and DOCX

Who it's for and when

Questions about transcribing interviews

How should I record an interview so it transcribes well?

Put the phone on the table between you, a little closer to the person answering, and switch on flight mode so a call doesn't cut the recording. Two clip-on microphones into one recorder work even better. For an interview on a video call, use the recording button of the call app itself. And ask for permission before you start recording.

Does the transcript show who is speaking?

No, speaker names are not added. The text comes in phrases, each with its timestamp. Questions and answers are usually easy to tell apart by meaning, so you mark the interviewer and the person you spoke to yourself, for example in Word.

Can I use the transcript in my thesis or dissertation?

Yes, the Word file is a good starting point for an appendix or for coding in your analysis software. Check it against the recording before you quote: names, technical terms and numbers are where mistakes happen. If your university asks for a set of transcription rules with pauses and overlaps, add those marks by hand.

How do I find quotes for an article?

For a recording of 10 minutes or more, “Key points” appears above the text. For an interview it shows the key ideas and the lines said word for word, each with a jump to its place in the text. You can also ask in your own words, for example for the five strongest quotes on one topic.

I have several interviews or a focus group. How do I get through them faster?

Pick up to 20 files at once. Each one is transcribed separately; when they are ready you see the text of each, tick the ones you need and download them together or merge them into one text. A focus group where people talk over each other comes out worse than a one-to-one interview, so plan time for checking.

What if the interview is longer than 120 minutes?

Free recordings can run up to 120 minutes. Recordings up to 7 hours are part of Wovea Plus, the paid subscription, with fair use of up to 100 hours of recordings a month; what it includes is on the Wovea Plus page.

Can I upload confidential interviews?

Nobody listens to the recording: it is transcribed automatically on our server, the file is deleted from there after 24 hours, and the text is kept in the library of this browser; it goes to your account only if you sign in. If your ethics approval or consent form does not allow uploading recordings to an online service, use the tool your institution provides.

What to do with the text next

More details

This page is for interviews you recorded yourself: a research interview for a thesis or a study, a conversation with an expert for an article, a user interview, a focus group. Typing up an hour of conversation by hand takes several times longer than the conversation itself. Here the first draft is ready in minutes, and your time goes into checking it and finding what matters.

Drop the file here or tap Choose a file. Audio from a voice recorder or a phone works (MP3, M4A, WAV, OGG, OPUS, FLAC, AAC, AMR), and so does the video of a call (MP4, MOV, WebM, MKV, AVI, 3GP). A recording can run up to 120 minutes and the file can be up to 2 GB; from a big file your browser can take out the sound so the upload is smaller. The language is detected on its own, or you can pick it before you start.

You get the text split into phrases, each with its timestamp, so any line can be checked against the recording. Speaker names are not added: mark the interviewer and the person you spoke to yourself, in Word or in your analysis software. Download Word (DOCX) for editing, TXT for coding tools, or SRT and VTT if the interview goes out as a video. The whole text can be translated into 45 languages.

For a recording of 10 minutes or more, “Key points” appears above the text. For an interview it shows the key ideas, the lines said word for word and the numbers and dates mentioned. Quotes stay in the language of the recording, with a translation underneath if “Key points” is in another language. You can also ask in your own words, for example for the answers about one topic only.

A study rarely has one interview. Pick up to 20 files at once: each is transcribed separately, and when they are ready you see the text of each, tick the ones you need, download them together or merge them into one text. A share link sends the text to a supervisor or co-author without the audio file and works for 30 days.

Quality depends on the recording. Two people close to one phone come out well; a busy café, a call on speakerphone or a focus group where people talk over each other cause mistakes, so check names, terms and numbers before you quote. The file is deleted from our server after 24 hours and the text stays in the library of this browser. It is free and needs no sign-up; to keep bots out, one connection can run up to 60 AI tasks an hour.