Can I anonymise participants before exporting?
Yes. Rename the speakers in the editor and correct any name that appears in the text, then export. The download reflects the edited transcript, not the original recording.
Academic transcription for research interviews
Thesis interviews, focus groups and fieldwork recordings — transcribed with speakers separated and timings kept, ready for coding.
- Speaker-separated, timestamped verbatim text
- TXT and DOCX for NVivo, MAXQDA and Atlas.ti
- Your audio is never used to train models
Start a transcript
Drop your file and pick a language.
Upload a file
Drop audio or video here
MP3, MP4, M4A, WAV, MOV and more
or paste a link
Picking the language improves accuracy. Leave it automatic if you are unsure.
By continuing you agree to our Terms of Service and Privacy Policy.
Transcription is the first step of the analysis
Coding starts from text, and the text has to be faithful: who spoke, in what order, at what point in the recording. Each turn is tagged and timed, so a quote in your chapter traces back to the minute it came from. Anonymise names in the editor before you export, and the exported file carries the change.
How it works
Three steps to your first transcript
-
Drop in your file
Audio or video of any length; the free plan transcribes the first 30 minutes of each file. MP3, MP4, M4A, WAV, MOV and a dozen more.
-
Pick the language
Leave the language on automatic or set it for better accuracy. Turn on speaker recognition if you need to know who said what.
-
Read, edit, export
The transcript opens with clickable timestamps — read it and fix a name straight away. A free account keeps it and exports it as TXT; DOCX, PDF, SRT and VTT come with the unlimited plan.
What happens to the recordings I upload?
They are stored for your account alone and are never used to train models, ours or anyone else’s. Delete the file and the audio goes with it.
Does it cope with focus groups?
Yes, with the usual caveat: the more people around one microphone, the harder they are to tell apart. A handful of distinct voices is handled well, and you can merge or rename speakers afterwards.
Start with one file
No account, no card. See the transcript before you decide anything.