To transcribe a phone call, send the call recording to the Potok bot on Telegram and switch on speaker labels. Files up to 2 GB work, far more than any call needs. You get two voices as Speaker 1 and Speaker 2. Ask for consent to record before the call starts.
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
- Consent to record comes first: tell the other person, and check the rules that apply in your country.
- Phone audio is narrow and compressed, so names, numbers and email addresses are the weak spots.
- With only two speakers, the labels are easy to map: the first voice is usually the caller.
How to do it
- Ask for consent. Say at the start that you are recording and why. Keep that sentence on the recording itself.
- Record the call. Use the recording tool of your phone or call system. Save it as audio rather than as a screen capture.
- Open the bot. Open @potok_now_bot in Telegram and start a chat with it.
- Switch on speaker labels. Two voices separate best when labels are on before you send the recording.
- Send the audio. Forward the recording or attach it as a file. For an unusually big file, up to 2 GB, use the Upload button of the mini app.
- Map the labels. Decide which number is your side and which is the customer. Rename them in the exported file.
- Check numbers and names. Listen again to phone numbers, order codes and spellings, then fix them in the text.
What the result looks like
[00:00] Speaker 1: Hello, you are speaking with the service desk. This call is recorded.
[00:05] Speaker 2: Hi, my parcel has not arrived and I have the order number.
[00:11] Speaker 1: Please read it slowly and I will look it up.
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 |
|---|---|---|
| Recording without telling the other person | You may break local rules and lose the customer's trust. | Say clearly that the call is recorded, and keep the notice on the audio. |
| Using speakerphone in a noisy room | Both voices blur and echo, so labels can swap mid-sentence. | Use a headset or a quiet room. |
| Trusting digits read aloud | Phone numbers and codes are short strings with no context to guess from. | Confirm every number by ear. |
| Sharing the transcript with everyone | Calls contain personal details that should not spread. | Send the text only to the people who need it. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Do I need permission to record a call?
Often yes. Rules differ by country and situation, so tell the other person and check the rules that apply to you.
Can the bot tell the caller from the agent?
It labels voices as Speaker 1 and Speaker 2 but does not know names. You decide which number belongs to whom.
Why are numbers often wrong in call transcripts?
Phone audio is compressed and digits come with no context. Read them back from the recording and fix them by hand.
Which export is best for a support team?
DOCX or PDF is easy to attach to a ticket, and TXT pastes into most tools without formatting trouble.
Can I send a voice message from a messenger instead?
Yes. The bot accepts voice messages and forwarded voice notes, and long results come back as a file.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Monaural (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