Get a text with timestamps from AAC files

By the Potok teamUpdated ~2 min read

AAC stores sound in small compressed chunks, so its internal count says little about minutes and seconds. For a text with timestamps from AAC files, send the recording to Potok in Telegram as 1 file. The reply shows normal clock times; keep the original file until you have checked 2 lines.

Turn a recording into text

Drop an audio or video file, or a voice message, into the chat with @potok_now_bot; the recognized text is sent back there.

Go to @potok_now_bot in Telegram

Export to TXT, MD, DOCX, PDF, SRT and VTT · files up to 2 GB · about 30 languages · speakers and timestamps on request

In short

  • The .aac extension is used for raw AAC bitstream files.
  • The Library of Congress describes AAC as a perceptual audio encoding format and cites ISO/IEC 14496-3.
  • One compressed AAC frame corresponds to 1024 PCM samples (21.33 ms at 48 kHz).
  • Potok accepts .aac files up to 2 GB and reads them without a conversion step.

What a AAC file is

PropertyValue
KindAudio codec (raw AAC stream, ADTS)
File extensions.aac, .m4a
What it holdsA perceptual audio encoding; a raw .aac file is an ADTS stream of self-synchronizing frames

How to get timestamps for AAC files

  1. Send the AAC file to the bot. In Telegram, open @potok_now_bot and attach the .aac file to the chat. Larger recordings, up to 2 GB, go through the Upload button in the bot's mini app.
  2. Mind this about the format. One compressed AAC frame corresponds to 1024 PCM samples (21.33 ms at 48 kHz).
  3. 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.
  4. Prepare this format. Send the .aac as it is; if your own player cannot open it, the file may be damaged, so fix that first.

What time marks look like

Example of a transcript with timestamps

[00:00] Speaker 1: And the striker runs down the left side.

[00:12] Speaker 1: A quick pass to the middle, and a shot!

[00:31] Speaker 1: The goalkeeper saves it with his fingertips.

[00:58] Speaker 1: Could you send me the photos from your cousin's wedding?

Lines written by us to show the layout. They are not output from a real AAC file.

Potok at a glance
OptionWhat it means
DigestPress the summary button under a finished transcript for a short digest
DictationA separate Potok desktop app lets you dictate text into any program; it recognises Russian speech
TranslationThe text keeps the language of the audio and is not translated
Upload limitFiles up to 2 GB
Output formatsTXT, MD, DOCX and PDF for text; SRT and VTT for subtitles

Typical AAC slips

Where things go wrong
SlipResultRemedy
Reading AAC frames as secondsA frame is a tiny slice, so the numbers look wrongUse the minutes and seconds in the transcript
Joining raw .aac pieces by simply copying them togetherPlayers misread the joined stream and the stamps driftJoin AAC pieces with an audio tool before sending
Trimming the AAC after the transcript is readyAll later stamps shift against the shortened fileRequest the transcript from the final AAC
Cutting the AAC file in a basic tool before sendingCut points may shift stamps from the original recordingSend the untouched original and trim only a copy

More

Terms used here are explained in the glossary. Handy helpers live in tools; apps are on the download page.

Common questions

Does Potok accept AAC files?

Yes. The bot accepts .aac 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 AAC files?

Android MediaRecorder offers an AAC_ADTS output format (Android MediaRecorder AAC_ADTS).

Sources

The dates show when each source was opened. Pages are edited over time; read the original before you rely on a detail.

  1. AAC, Advanced Audio Coding (Library of Congress), Library of Congress · checked
  2. ADTS, Audio Data Transport Stream (Library of Congress), Library of Congress · checked
  3. AAC encoder, Microsoft Learn · checked

Check it on a file of your own

Send your voice message, audio or video to @potok_now_bot on Telegram and the text comes back in the chat.

Go to @potok_now_bot in Telegram