To transcribe a research interview, send the recording to the Potok bot on Telegram with speaker labels switched on. Files up to 2 GB work. The draft is a base for verbatim text: you then compare it with the audio and add hesitations and pauses your method requires.
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
- Verbatim text keeps the words as spoken, so a draft needs your edit for false starts, laughter and repeated words.
- Consent and data care apply to the file as well as the recording: where it is stored and who sees it.
- Interviewer and participant labels are numbers, so a codebook or key kept apart from the text links them to real people.
How to do it
- Check your consent form. Confirm that it allows the use of a cloud tool for transcription. If your ethics board has rules, follow them.
- Decide the transcript style. Choose full verbatim or clean verbatim before you start, and write the rule down for your project.
- Open the bot. Open @potok_now_bot in Telegram and start a chat with it.
- Switch on speaker labels. An interview has at least two voices. Labels make the question-and-answer turns easy to code.
- Send the recording. Attach the audio as a file. A long field interview, up to 2 GB, can go through the Upload button of the mini app.
- Compare with the audio. Play the recording at normal speed and correct each line. Add pauses and non-verbal sounds as your method requires.
- Anonymise and store. Replace names and places with codes, store the key separately, and keep the audio under the same protection.
What the result looks like
[00:00] Speaker 1: Can you describe how you first started studying part time?
[00:06] Speaker 2: Well, I, I started because my job changed and I needed a new qualification.
[00:14] Speaker 1: What was the hardest part?
[00:17] Speaker 2: Finding time, honestly. Evenings mostly.
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.
| Feature | Details |
|---|---|
| Where it works | Telegram bot @potok_now_bot; large files go through the bot's mini app |
| File size | Up to 2 GB |
| Export | TXT, MD, DOCX, PDF, SRT, VTT |
| Speakers and time | Speaker labels and timestamps can be switched on |
| Languages | About 30 languages with good published results; a few more with warnings |
| Translation | The transcript is not translated into another language |
| Dictation | A separate Potok desktop app lets you dictate text into any program; it recognises Russian speech |
Common mistakes
| Mistake | What happens | Fix |
|---|---|---|
| Treating a draft as verbatim | Small words and repairs are missing, which can matter in discourse analysis. | Edit against the audio line by line. |
| Keeping names in the shared file | Participants could be identified if the file leaks. | Use codes in the text and store the key in another place. |
| Mixing transcript styles in one project | Your coding becomes inconsistent across interviews. | Write the style rules once and apply them to every file. |
| Forgetting that the file is data | Copies spread across phones and drives with no record. | Keep a list of where each interview file lives and delete extra copies. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Is the first draft verbatim?
It is a close start, but you must compare it with the audio. Repeats, fillers and pauses may need to be added or removed.
Can I use it for sensitive interviews?
Check your consent form and ethics rules first. Some projects forbid cloud tools or require extra safeguards.
How do I keep participants anonymous?
Replace names with codes in the text, and keep the key that links codes to people in a separate protected place.
Which export is best for coding software?
DOCX and TXT are the formats most analysis tools can import. Check your software's list before you choose.
Can the transcript show interviewer and participant?
Labels appear as numbers. Rename them to Interviewer and Participant 1 in the exported file.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Transcription (linguistics) (Wikipedia), Wikipedia · checked
- Speaker diarisation (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