Focus group transcription with every participant identified
The verbatim is the raw material of qualitative research, but producing it by hand devours entire days. Verlio transcribes the session attributing each contribution to moderator and participants, so you can move straight to what matters: the analysis and the quotes for the report.
How it works — in 3 steps.
Upload the session
Audio from the table recorder or video from the online session: the file goes in as-is. If the study involves several groups, you can upload them together and keep them separate or merge them into one document.
The AI separates moderator and participants
Every contribution is attributed to the right voice, up to 8 and more speakers. Attach the discussion guide as context and the study's key concepts, brand names and product names are transcribed without mangling.
Download verbatim and summary
Export the full verbatim to Word or PDF for coding, or the Structured Document that groups the discussion by theme, with key points and a glossary: a first layer of analysis already done.
The verbatim is the bottleneck of qualitative research
A 90-minute session with six participants can take days of manual transcription, and until the verbatim exists the analysis can't start: thematic coding, cross-group comparison and report writing all sit in the queue.
Automating this step compresses delivery timelines. The afternoon session is a document by the same evening, and the researcher works on the content while memory is fresh — when the body language and the mood of the group are still vivid.
Eight people talking over each other: can the recognition cope?
Verlio's speaker recognition is built to handle up to 8 and more voices, the typical scenario of a moderated focus group. Brief overlaps — inevitable when the group warms up — are handled; on very heated exchanges, the quality of the audio capture matters most.
Two tricks help a lot: a recorder in the middle of the table, closer to the participants than to the moderator, and a round of introductions at the start of the session, which makes renaming the voice labels with real profiles immediate.
Verbatim quotes ready for the report
Participants' exact words are what gives a qualitative report its force. With a transcript attributed voice by voice, pulling faithful quotes and matching them to the right profile takes seconds, and labels can stay anonymous to protect participants.
All processing happens on servers in the European Union in compliance with the GDPR — a requirement research agencies and end clients increasingly write into their briefs. Files are deleted from the account when the study is closed.
Frequently asked questions.
How many participants can it tell apart?
Up to 8 and more voices, moderator included: the standard size of a focus group fits comfortably.
How much does it cost to transcribe a 90-minute focus group?
3 credits, because 1 credit covers 30 minutes of recording. Packs start at €5, with no subscription: ideal for project-based work.
The group spoke one language but the report is due in another: possible?
Yes. Verlio transcribes the session in the original language and can generate the document in any of the more than 35 languages available.
Is participants' data handled under the GDPR?
Yes: processing and storage happen in the European Union, and you can delete the recordings at any time, in line with your study's privacy notices.
Can I test the service on a pilot session?
Yes: you get 1 free hour at signup, no card, and every file under 10 minutes is always free. Enough to judge the output on your real setting.
You might also need.
Try it on your own file, right now.
Upload an audio or video file, choose the document language and download the result as Word or PDF. Your first hour is free and we never ask for a card.