Focus groups and qualitative interviews, with participants already separated.
Verbatim ready to import into NVivo, ATLAS.ti or MAXQDA. Every speaker identified, timestamps to the second, your field's terminology respected. Stop paying an assistant or spending the weekend on rewind.
It used to steal your hours. Now it gives you time back.
One 90-min focus group = 10–15 hours of transcription
One 90-min focus group = 9 minutes and 3 credits (≈€2.70)
A research assistant at €200+ for the transcription
€9 in credits = 5 hours of focus groups transcribed
Coding blocked until the verbatim is ready
Verbatim same-day, start your analysis right away
Not a transcript.
A professional report.
From a one-hour focus group or qualitative interview, the Structured Document produces material ready for analysis: summary, key themes, sections, highlighted data — participants, frequencies, quotes — and a final glossary.
The AI recognises that it's a qualitative interview or a focus group and organises the content like the first draft of your thematic analysis.
Focus group: consumer habits
Executive summary
Key points
Participants
8
Themes
6
Glossary
Built for your workflow.
Up to 8 participants identified
Multi-speaker diarisation built for focus groups, not just two-person meetings. Every contribution attributed to the right person — with larger groups, a microphone at the centre of the table gives the best results.
Verbatim or cleaned text — your choice
Verbatim output with hesitations and repetitions (for conversation analysis) or text cleaned of pauses and ums (for publications and quotations).
Your field's terminology
Upload a PDF with your disciplinary glossary (sociology, anthropology, nursing science, etc.) and the AI respects it — no more 'Fuko' instead of 'Foucault'.
How it works — in 4 steps.
No installs, no plugins. Open your browser and go.
- 1
Record the session
A single microphone at the centre of the table, a smartphone app, a recorded Zoom call. It works with everything.
- 2
Upload to Verlio
Drag-and-drop from your browser. Even a 2-hour focus group in one go. No splitting, no plugins.
- 3
The AI separates the participants
It recognises every voice, adds timestamps, labels 'Speaker 1, 2, 3…'. You rename them with real names (or anonymous codes).
- 4
Export for analysis
.docx ready for NVivo/ATLAS.ti, or TXT/PDF to share with your team. Ready for coding.
When you really need it.
PhD theses
Methodology chapters with 100% accurate verbatim, timestamped quotations.
Social research
Ethnographic studies, biographical interviews, narrative inquiry.
Qualitative clinical studies
Patient experience, focus groups with patients, nursing and care research.
Market research
Consumer focus groups, in-depth customer interviews, UX research.
It's not just transcription
No more replaying the audio and typing everything up by hand. Upload your file and within minutes you have the document ready to deliver — with speakers identified and terminology done right.
0+
transcription languages
0%+
terminology accuracy, with a context document
0h+
of audio per single upload
0%
data processed and stored in the EU
Questions we hear often.
Is the output compatible with NVivo and ATLAS.ti?
+
Yes. We export to .docx with the standard 'Speaker: text' structure that NVivo and ATLAS.ti recognise automatically for auto-coding. TXT and PDF are also available if you prefer to process with Python or R scripts.
How accurate is participant recognition?
+
In a well-run focus group (one microphone at the centre, participants not talking over each other too much) diarisation is above 90%. On overlaps the AI makes its best attempt and you correct in the dashboard before export. Our speaker accuracy is among the highest on the market.
Can I rename participants while preserving anonymity?
+
Yes. After transcription you rename speakers with anonymous codes (P1, P2, P3…) or pseudonyms. Files remain editable in the dashboard before export, and you can remove real names if they were ever spoken in the recording.
Does the data meet GDPR requirements for informed consent?
+
Files are processed on servers in the European Union, encrypted at rest and in transit. They are never used to train models, and you can delete them from the dashboard at any time. For studies under ethics committee oversight, on request we sign a standard EU DPA as data processor.
Can I upload a glossary for specialist terms?
+
Yes. For each file you can attach a reference document — theoretical papers, glossaries, your group's previous publications. The AI uses that context to spell proper names, theoretical constructs and field terminology correctly.
Can I also use it for individual interviews, not just focus groups?
+
Of course. Two-voice in-depth interviews, narrative inquiry, oral history: same workflow, same accuracy. On a two-person interview, diarisation is virtually perfect.
Your next verbatim: same day. Not next week.
Sign up free, get welcome credits and upload your first focus group or interview right now.
5 minutes for an hour of audio · data processed in the EU