To convert a WAV to text, send the file to the Potok bot on Telegram and read the transcript in the chat. WAV is uncompressed, so size is the real limit: stereo at 44.1 kHz and 16 bits takes about 10.6 MB per minute, so 2 GB covers a little over three hours.
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
- WAV usually holds uncompressed PCM audio, so files are large and a short session can already weigh hundreds of megabytes.
- One hour of that stereo audio is about 636 MB, computed as 10.6 MB per minute times 60.
- Speech does not need CD quality. A mono copy is half the size and is a common way to fit a long session.
- Studio and field recorders write WAV, so a file straight from a recorder is usually the best source.
How to do it
- Read the size of the file. Look at the size in your file manager. At about 10.6 MB per minute you can also estimate it from the length.
- Shrink only if it is over 2 GB. Cut the file into parts, or save a mono copy. Do not switch to a very low-bitrate MP3.
- Open the bot. Open @potok_now_bot in Telegram.
- Send the WAV. Attach it as a document. Files up to 2 GB go through the Upload button of the mini app.
- Collect the text. A short transcript appears in the chat. A long one arrives as a file.
- Export. Save as TXT, MD, DOCX, PDF, SRT or VTT.
What the result looks like
[00:00] Speaker 1: Recording on site, north wall, the crack runs along the lower part.
[00:07] Speaker 1: It is about as long as my forearm and reaches the window frame.
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 |
|---|---|---|
| Uploading a four-hour WAV without counting | At about 10.6 MB per minute that file is roughly 2.5 GB and does not fit. | Split it into parts under 2 GB, or save a mono copy first. |
| Compressing the WAV to a tiny MP3 just to shrink it | Heavy compression removes detail from quiet speech. | Reduce channels or sample rate instead, or cut the file. |
| Leaving a long pause at the start of a studio take | Minutes of silence still count towards the file size. | Trim the silent start and end before sending. |
| Recording a group with only one channel active | One side of the room is quiet, and its speakers are missed or garbled. | Check that every microphone track is in the file you send. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
How big is a WAV file per minute?
Stereo at 44.1 kHz and 16 bits takes about 10.6 MB per minute, so one hour is roughly 636 MB.
How many hours fit in 2 GB?
A little over three hours of that stereo audio. Mono, or a lower sample rate, lets you fit more.
Should I convert the WAV to MP3 first?
Not unless the file is too big. A moderate bitrate for speech is fine; a very low one hurts the text.
Can I send the WAV as a document?
Yes. Send it as an audio file or a document, and use the Upload button for large ones.
Does WAV give a better transcript than other formats?
It keeps all the detail, but a clear voice and low noise matter more than the container.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- WAV (Wikipedia), Wikipedia · checked
- Megabyte (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