To turn a WhatsApp voice message into text, share it from WhatsApp to Telegram and send it to the Potok bot. Short results come back in the chat, and files up to 2 GB are supported. Export TXT, MD, DOCX, PDF, SRT or VTT. It works in about 30 languages.
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
- The bot lives in Telegram, so a WhatsApp message has to be shared out of WhatsApp and into a chat with the bot.
- WhatsApp voice messages use the Opus codec, which is built for speech and keeps files small.
- Send messages one at a time, so each transcript matches its message.
- Mixed-language messages are the hardest case: check the verdict for your language before you rely on the text.
Send a WhatsApp voice message to the bot
WhatsApp has no bot of ours, so the message makes a short trip through Telegram:
- Find the voice message in WhatsApp. Open the chat and press and hold the message.
- Share it to Telegram. Use the share or forward option and choose Telegram. The names of the menu items depend on your phone and the WhatsApp version, so check WhatsApp Help if you do not see them.
- Pick the bot. In Telegram, choose the chat with @potok_now_bot and send the message.
- Wait for the text. A short message comes back in the chat. A long one comes back as a file.
- Copy or export. Copy the text, or export it as TXT, MD, DOCX, PDF, SRT or VTT.
What the transcript looks like
The example below is text we wrote to show the layout of a transcript with times and a speaker number. It is not a real recording.
[00:00] Speaker 1: Hi, it's Maria. I'm outside the pharmacy on Oak Street.
[00:05] Speaker 1: Can you bring the blue folder? It's on the second floor, door fourteen.
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 the audio is
WhatsApp voice messages are short clips saved with the Opus codec, which is built for speech. Opus keeps files small and the voice clear. If you share several messages, send them one by one so that each transcript is easy to match to its message.
Languages
Voice messages often mix languages, with a name or a word from another language inside a sentence. Potok works in about 30 languages with good published results, and a few more with warnings. Check the verdict for your language on the list of languages. For an example of how a language is described, see Spanish transcription.
Common mistakes
| Mistake | What happens | Fix |
|---|---|---|
| Forwarding the message to another WhatsApp chat | It never leaves WhatsApp, so the bot never receives it. | Use the share option and choose Telegram, then the chat with the bot. |
| Sending a whole exported chat | An archive of a chat is not a recording, so there is nothing to transcribe in it as it is. | Share the voice messages you need, one by one. |
| Reading a mixed-language message as if it were one language | Names and words from another language inside a sentence are the likeliest to come out wrong. | Check those words against the audio, and see the verdict for your language on the language list. |
| Transcribing someone else's message without asking | It is their voice, and the audio travels through Telegram to the bot. | Ask first, and keep the original message in WhatsApp. |
Other ways to record: read about Telegram voice messages, or the guide to turning an MP3 file into text.
Frequently asked questions
Do I need to install anything to transcribe a WhatsApp voice message?
You need Telegram, because the bot lives there. You do not need to install anything else. Share the voice message from WhatsApp to Telegram and send it to the bot.
Can I transcribe a long WhatsApp voice message?
Yes. The bot supports files up to 2 GB, and a long transcript arrives as a file.
In which languages can I transcribe WhatsApp voice messages?
In about 30 languages with good published results, plus a few more with warnings. See the full list of languages for the verdict on each.
Is the WhatsApp voice message sent to WhatsApp or Telegram again?
You send it from WhatsApp to a chat with the bot in Telegram, so the audio travels through Telegram to the bot. Do not send recordings you are not allowed to share.
Can I get the transcript as a document?
Yes. Export it as DOCX, PDF, TXT, MD, or as SRT or VTT subtitle files.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- WhatsApp (Wikipedia), Wikipedia · checked
- Opus audio format (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