Forward the WAV file to Potok in Telegram, and the reply is a text with timestamps for every spoken passage. A multi-hour recording is safer sent in 2 or more parts, so write down where each part starts. Then add that offset to the stamps of later parts.
Transcribe a recording
In Telegram, write to @potok_now_bot and add your file. The finished text appears in the conversation when recognition ends.
Go to @potok_now_bot in Telegram
Up to 2 GB per file · speaker labels and timestamps · six export formats · about 30 languages
Facts that matter here
- Android documents WAVE (.wav) with 8- and 16-bit linear PCM.
- WAVE is a subtype of the RIFF container format.
- In a PCM WAV file the time unit is one sample, which lasts 1 / sample rate seconds.
- Send .wav files up to 2 GB as they are: Potok decodes them without a separate conversion.
WAV at a glance
| Property | Value |
|---|---|
| Kind | Audio file (RIFF container, usually PCM) |
| File extensions | .wav |
| What it holds | A RIFF container; the 4 GB barrier of RIFF/WAVE comes from 32-bit addressing |
How to get timestamps for WAV files
- Upload the .wav file. Start a chat with @potok_now_bot and upload the WAV file. Each file may be up to 2 GB, and the Upload button in the mini app handles the largest ones.
- Keep the format in mind. In a PCM WAV file the time unit is one sample, which lasts 1 / sample rate seconds.
- Switch on timestamps. Open the other-format options under the result, turn on timestamps (speaker labels can be added there too) and check three marks against the sound.
- Prepare this format. A WAV file is large: a long recording can reach the 2 GB limit, so for hours of speech use the Upload button.
What time marks look like
[00:00] Speaker 1: Your novel is set in a small fishing town.
[00:12] Speaker 1: Yes, I spent a summer there as a child.
[00:31] Speaker 1: The sea almost became a character in the book.
[00:58] Speaker 1: The garden needs watering every evening during the hot weeks.
Lines written by us to show the layout. They are not output from a real WAV file.
| Topic | Answer |
|---|---|
| Labels and times | Speaker labels and timestamps are optional switches |
| What you can send | Audio, video and voice messages |
| File size | Up to 2 GB |
| Where it works | The Telegram bot @potok_now_bot, plus its mini app for big uploads |
| Typing by voice | For dictating into other programs there is a separate Potok desktop app that recognises Russian speech |
Common mistakes with WAV files
| What goes wrong | Effect | What to do |
|---|---|---|
| Splitting the WAV into parts without noting offsets | Part two stamps restart from zero and confuse the notes | Name parts clearly or send the whole WAV once |
| Trimming silence from the WAV after the transcript | Later stamps no longer match the shortened recording | Trim silence first, then request the transcript |
| Sending a multi-hour WAV in one piece | Finding a line in one huge transcript becomes slow | Split long WAV sessions by topic before sending |
| Treating the stamp as the exact start of each word | Quotes cut from the audio may begin a bit late or early | Leave a couple of seconds before each stamp when cutting |
Next steps
See the tools, the glossary and the download page for converters, explanations of terms and the apps.
Frequently asked questions
Can I send WAV files straight to Potok?
Yes. .wav files up to 2 GB go to the bot as they are; there is no conversion step before recognition.
Do the time marks depend on the WAV format?
The marks point to a place in the recording so you can find it again. Check a few against the sound before you quote them.
What do the specifications say about WAV?
Android documents WAVE (.wav) with 8- and 16-bit linear PCM. WAVE is a subtype of the RIFF container format.
Sources
We opened each page below on the date shown. Because pages get updated, confirm important details at the source.
- WAVE audio file format (Library of Congress), Library of Congress · checked
- EBU Tech 3306: RF64, an extended file format for audio, EBU · checked
- Supported media formats, Android Developers · checked
- WAVEFORMATEX structure, Microsoft Learn · checked
Run your own recording through it
Drop an audio or video file, or a voice message, into the chat with @potok_now_bot; the recognized text is sent back there.
Open @potok_now_bot in Telegram