Transcribe a focus group

By the Potok teamUpdated ~2 min read

To transcribe a focus group, send the recording to the Potok bot on Telegram with speaker labels and timestamps on, then export DOCX. Files up to 2 GB work. Market researchers get the full text with times, ready to code into themes and quote in the report.

Transcribe a recording

Send your voice message, audio or video to @potok_now_bot on Telegram and the text comes back in the chat.

Open @potok_now_bot in Telegram

Files up to 2 GB · export to TXT, MD, DOCX, PDF, SRT and VTT · speaker labels and timestamps · about 30 languages

Key facts

  • A focus group often has six or more voices, so labels can drift where speakers overlap.
  • Researchers tag the text by theme, and timestamps let them return to the audio for tone and hesitation.
  • Participants usually need to give consent, and the report often hides their names.

How to do it

  1. Plan the room. Seat people so the recorder is about equally close to everyone, and give the moderator a clear lead role.
  2. Record the consent. Start the recording with the participants agreeing, so the consent is on the tape.
  3. Open the bot. Open @potok_now_bot in Telegram and send the recording.
  4. Switch on speaker labels and timestamps. Both are needed for coding and quoting.
  5. Make a participant key. Listen to each speaker's first lines and write a key that maps the labels to participant codes.
  6. Code the text. Tag passages with themes in your analysis tool or in the margins of the DOCX.
  7. Pick quotes with times. Copy each quote with its timestamp so you can verify it in the audio.

What the result looks like

Example: a moderator and two participants

[00:00] Speaker 1: Let's talk about the last time you bought this product. What made you choose it?

[00:06] Speaker 2: Honestly, the price, and a friend recommended it.

[00:11] Speaker 3: For me it was the packaging. It looked trustworthy.

[00:16] Speaker 1: Interesting, say more about that.

Sample text written by us to show the layout of a transcript. It is not the output of the recognition engine and not a real recording.

What Potok can do
FeatureDetails
Where it worksTelegram bot @potok_now_bot; large files go through the bot's mini app
File sizeUp to 2 GB
ExportTXT, MD, DOCX, PDF, SRT, VTT
Speakers and timeSpeaker labels and timestamps can be switched on
LanguagesAbout 30 languages with good published results; a few more with warnings
TranslationThe transcript is not translated into another language
DictationA separate Potok desktop app lets you dictate text into any program; it recognises Russian speech

Common mistakes

Common mistakes and how to fix them
MistakeWhat happensFix
Letting the moderator talk too muchThe transcript is full of questions and the participants' views get thin.Prepare short prompts and let silence work.
Not noting who is whoAfter a few weeks the labels mean nothing.Write the participant key right after the session.
Using full names in the reportParticipants may be identifiable.Replace names with codes before you publish.
Coding from the text aloneTone and sarcasm do not show in text.Replay marked sections before you rely on a quote.

More

See the full list of languages, the tools and the glossary.

Frequently asked questions

How many participants can the labels handle?

Labels can be switched on for several voices. Overlap lowers reliability, so check busy moments in the audio.

Why do researchers want timestamps?

To return to the audio for tone and to verify quotes.

Which export suits coding?

DOCX for margin notes. TXT works if you load the text into analysis software.

Can I hide participants' names?

Yes. The labels are numbers, and you can replace them with codes in the file.

Is consent needed?

In most research, yes. Record the agreement at the start and follow your ethics rules.

Sources

Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.

  1. Speaker diarisation (Wikipedia), Wikipedia · checked
  2. Crosstalk (Wikipedia), Wikipedia · checked

Try it on your own recording

Send your voice message, audio or video to @potok_now_bot on Telegram and the text comes back in the chat.

Open @potok_now_bot in Telegram