To transcribe oral history, send each interview to the Potok bot on Telegram with timestamps on. Files up to 2 GB work, which covers many hours of talk. Then export the text in the archive formats your collection prefers, and keep the audio next to it.
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
- Archive formats here means plain TXT for long-term safety and PDF for a fixed reading copy.
- A long interview is better split into one file per session, so a lost file costs you one sitting.
- Timestamps let a reader return from a page of text to the exact minute of the voice.
How to do it
- Label the recording. Write the speaker, place and session number into the file name before you send it. Names inside the file are easier to keep than notes on paper.
- Check the sound once. Play a minute from the start and the middle. Old tape copies and phone recordings differ a lot in quality.
- Open the bot. Open @potok_now_bot in Telegram and start a chat with it.
- Switch on timestamps. A page of an hour-long talk is hard to navigate without times. Turn them on before sending.
- Send the file. Attach the audio as a file. For a very long session, up to 2 GB, use the Upload button of the bot's mini app.
- Read it with the person in mind. Fix family names, villages and nicknames. Mark unclear parts in square brackets rather than guessing.
- Export and store. Save TXT for the archive and PDF for sharing. Store the audio, the text and your notes in one folder.
What the result looks like
[00:00] Speaker 1: Tell me about the house where you grew up.
[00:05] Speaker 2: It stood near the river, with a small orchard behind it.
[00:12] Speaker 2: We carried water from the well every morning [unclear].
[00:19] Speaker 1: And who lived there with you?
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 |
|---|---|---|
| Keeping only the transcript | Tone, pauses and laughter are lost, and the text cannot be re-checked later. | Archive the original audio next to every transcript. |
| Storing the text only in one editor format | A file that opens only in one program may be unreadable in the future. | Keep a plain text copy alongside DOCX or PDF. |
| Guessing at unclear words | A guessed name can enter the family record as fact. | Mark the gap with a bracket and the time, and ask a relative later. |
| Sending one huge file for a whole day of recording | A single failure forces you to start over. | Send one file per session and number them. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Can I transcribe several hours of recording?
Yes, as long as each file is within the 2 GB limit. Splitting by session keeps the work easier to manage.
Which export suits an archive?
TXT is the safest plain copy, and PDF gives a fixed layout. DOCX is useful while you are still editing.
Will it understand an older speaker or a local accent?
Quality varies with the voice and the recording. Plan to read the draft with the audio, and mark unclear words.
Can the transcript show who is talking?
Speaker labels can be switched on and appear as numbers. Replace them with names from your session notes.
What about consent for the recording?
Get the narrator's agreement in writing or on the tape, and say how the text will be kept and shared.
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
- Text file (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