To turn a Telegram voice message into text, forward it to the Potok bot and the transcript comes back in the same chat. The bot also takes audio files, video and YouTube links, with files up to 2 GB. Export TXT, MD, DOCX, PDF, SRT or VTT. About 30 languages work.
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
- Telegram stores a voice message as Opus audio in an OGG container, so a saved one is a small OGG or OPUS file.
- Forward the message from any chat you can open. You do not have to download it first.
- Telegram Premium has its own voice transcription. The bot adds audio files, video, long recordings, speaker labels and document export.
- Speaker labels are numbers such as Speaker 1, never real names.
Forward a voice message to the bot
The whole job takes four steps and no download:
- Open the chat with the voice message. It can be a private chat, a group or a channel, as long as you can open the message.
- Forward it to the bot. Choose Forward on the message and pick @potok_now_bot. The menu names differ a little between apps and versions.
- Wait for the text. A short message comes back in the chat. A long recording comes back as a file.
- Copy or export. Copy the text from the chat, or export it as TXT, MD, DOCX, PDF, SRT or VTT.
You can send the same bot an audio file, a video or a YouTube link. For a large file, up to 2 GB, use the Upload button of the bot's mini app.
What the transcript looks like
With timestamps and speaker labels on, every passage starts with a time and a speaker number. The example below is text we wrote to show the layout. It is not a recording.
[00:00] Speaker 1: Running late, the train is stuck outside the station.
[00:04] Speaker 1: Start without me and put the budget first.
[00:08] Speaker 1: I will join around half past nine.
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 |
What a Telegram voice message is
Telegram sends voice messages as Opus audio in an OGG container. Opus is a codec built for speech, so files stay small and the voice stays clear. If you save a voice message, you get an OGG or OPUS file, and the bot can transcribe audio files as well.
Telegram Premium or the bot
Telegram Premium has its own transcription of voice messages. Potok is a different tool for different jobs: it handles audio files, video, long recordings, speaker labels, timestamps and export to documents and subtitle files. If all you need is a quick look at a short note inside the chat, the built-in feature may be enough.
Languages and quality
The bot works in about 30 languages with good published results, plus a few more with warnings. The figures come from tests by other people, not from tests by Potok. See the list of languages, or read how quality looks for Japanese.
Common mistakes
| Mistake | What happens | Fix |
|---|---|---|
| Forwarding a recording you have no right to share | A voice is personal data, and the audio travels through Telegram to the bot. | Ask the speaker first, or transcribe only your own messages. |
| Sending one long talk as many separate voice messages | You get one transcript per message and the context breaks at every cut. | Paste the texts into one document in the right order, and read it as a whole. |
| Trusting names and numbers in the text | These are the places where recognition fails most often. | Replay those seconds and correct the text. |
| Deleting the original message | A transcript is a convenient copy and can contain mistakes, so you lose the way to check it. | Keep the original voice message until the text is final. |
A longer conversation needs its own routine: read the guide on transcribing an interview. For an MP3 file, see MP3 to text. Chats in another messenger work the same way: see WhatsApp voice messages.
Frequently asked questions
How do I send a Telegram voice message to the bot?
Forward the voice message to the chat with the bot. You can forward it from any chat that you can access.
Does Telegram have its own voice to text?
Telegram Premium includes a built-in transcription of voice messages. Potok is a separate bot that also takes audio files, video and long recordings and exports the text in several formats.
Can I transcribe a voice message from a group chat?
Forward it to the bot in a private chat. Do not send recordings you are not allowed to share.
How long can the voice message be?
The bot supports files up to 2 GB. A long transcript arrives as a file instead of a chat message.
Can I get speaker labels?
Yes, speaker labels and timestamps can be switched on. The labels are numbers, such as Speaker 1 and Speaker 2, not real names.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Telegram Bot API, sendVoice, Telegram · checked
- Opus audio format (Wikipedia), Wikipedia · checked
- Telegram (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