Pass the AVI file to Potok in Telegram, and you get back a text with timestamps based on the soundtrack. Times follow the sound, not frame numbers, so a delayed audio stream can leave stamps off from the picture. Play 1 scene beside the transcript before relying on it.
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
About 30 languages · speaker labels and timestamps · files up to 2 GB · export to TXT, MD, DOCX, PDF, SRT and VTT
Facts that matter here
- OpenDML extensions specify multiple RIFF chunks that bring capacity to whatever the filesystem supports.
- AVI files generally contain multiple streams of different data types, usually audio and video.
- The AVI stream header gives samples per second as dwRate divided by dwScale (dwRate / dwScale).
- Send .avi files up to 2 GB as they are: Potok decodes them without a separate conversion.
About the AVI format
| Property | Value |
|---|---|
| Kind | Container (RIFF) |
| File extensions | .avi |
| What it holds | A RIFF file with the form type "AVI " that holds streams of different data types, usually audio and video |
How to get timestamps for AVI files
- Open the bot and send the file. Open @potok_now_bot in Telegram and send the .avi file. Files up to 2 GB are accepted; for a long recording use the Upload button of the bot's mini app.
- Mind this about the format. The AVI stream header gives samples per second as dwRate divided by dwScale (dwRate / dwScale).
- Turn on time marks. Under the result open the other-format options and enable timestamps; before you quote a mark, jump to that place in the file and listen.
- Prepare this format. An AVI from old equipment can hold audio in unusual codecs; if the bot cannot read the file, convert it to MP4 first.
What time marks look like
[00:00] Speaker 1: Welcome to our annual school play, everyone.
[00:12] Speaker 1: Please turn off your phones and enjoy the show.
[00:31] Speaker 1: The first act starts with the village scene.
[00:58] Speaker 1: We painted the hallway yellow, and it looks much brighter now.
Lines written by us to show the layout. They are not output from a real AVI file.
| Option | What it means |
|---|---|
| Spoken languages | About 30 languages with good published results and a few more with warnings |
| Summary | The result message has a summary button for a digest of the text |
| Where it works | In Telegram, through @potok_now_bot; the bot's mini app takes large files |
| Accepted | Voice messages, audio files and video files |
| Dictation | A separate Potok desktop app lets you dictate text into any program; it recognises Russian speech |
Where AVI files go wrong
| Slip | Result | Remedy |
|---|---|---|
| Using AVI frame numbers instead of times | The transcript lists times, so frame numbers do not match | Jump in the player by minutes and seconds |
| Sending an AVI with a delayed audio stream | Stamps follow the sound and look late against the picture | Fix the audio sync in the AVI first |
| Repairing the AVI index after transcription | A rebuilt file can change the playback start and stamps | Repair the AVI first, then request the transcript |
| Giving the transcript to an editor without the matching AVI | They cannot verify stamps and waste time on guesses | Share the transcript and the exact AVI file together |
Where to look next
The tools section has converters and calculators, the glossary explains the terms, and the download page covers the apps.
Common questions
Does Potok accept AVI files?
Yes. The bot accepts .avi files up to 2 GB, so no conversion is needed first.
Can timestamps be combined with speaker labels?
Yes. Both can be switched on in the other-format options, and the result is shown again with the marks you chose.
Which apps and devices create AVI files?
The DirectShow AVI Mux filter lets capture applications save AVI files (DirectShow AVI Mux).
Sources
Every source below was checked by hand on the date given. Sites change, so open the source if the exact wording matters.
- AVI RIFF file reference, Microsoft Learn · checked
- OpenDML AVI extensions (Library of Congress), Library of Congress · checked
- AVI stream header (AVISTREAMHEADER), Microsoft Learn · checked
See the result on your recording
Drop an audio or video file, or a voice message, into the chat with @potok_now_bot; the recognized text is sent back there.
Write to @potok_now_bot in Telegram