AIFF to text

By the Potok teamUpdated ~2 min read

To convert an AIFF file to text, send it to the Potok bot on Telegram and the transcript returns in the chat. AIFF is Apple's uncompressed audio format, similar in size to WAV, so CD quality stereo takes about 10.6 MB a minute and a 2 GB file holds about three hours. Export TXT, DOCX, PDF, SRT or VTT.

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

  • AIFF is similar in size to WAV, so long sessions grow fast: an hour of CD quality stereo is more than 600 MB.
  • Speech does not need CD quality, so a mono copy at a lower sample rate is a common way to shrink a long take.
  • The extension may be .aif or .aiff, and both mean the same format.
  • Timestamps help when you need to find a spot in a long studio session.

How to do it

  1. Estimate the size. Multiply the minutes by about 10.6 MB for CD quality stereo. The audio file size calculator does the sum for other settings.
  2. Decide whether to shrink it. If the file is over 2 GB, export a mono copy from your audio editor, or cut the session into parts.
  3. Open the bot. Start the chat with @potok_now_bot in Telegram.
  4. Send the AIFF. Use the Upload button of the bot's mini app for large files. Smaller ones go as an audio file or a document.
  5. Choose output. Switch on speaker labels for a conversation, then export DOCX or TXT.

What the result looks like

Example: a studio interview take as a transcript

[00:00] Speaker 1: Levels are fine, we can start the take.

[00:03] Speaker 2: Should I say my name first?

[00:06] Speaker 1: Yes, then tell us how the project began.

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.

What Potok can do
FeatureDetails
Where it worksTelegram bot @potok_now_bot; large files go through the bot's mini app
File sizeUp to 2 GB
ExportTXT, MD, DOCX, PDF, SRT, VTT
Speakers and timeSpeaker labels and timestamps can be switched on
LanguagesAbout 30 languages with good published results; a few more with warnings
TranslationThe transcript is not translated into another language
DictationA separate Potok desktop app lets you dictate text into any program; it recognises Russian speech

Common mistakes

Common mistakes and how to fix them
MistakeWhat happensFix
Sending a six hour session in one pieceAt about 10.6 MB a minute the file passes the 2 GB limit.Split the session at a pause, or save a mono copy first.
Exporting a multichannel mix when only voices matterExtra channels make the file bigger without helping recognition.Export a stereo or mono mix of the voices.
Sending each stem of a project separatelyYou get several partial transcripts and no sense of who said what in order.Bounce one mixed file with all speakers.
Squeezing the file into a tiny MP3 just to send itHeavy compression removes detail that the AIFF was keeping.Keep 64 kbps or more for speech if you must compress.

More

See the full list of languages, the tools and the glossary.

Frequently asked questions

What is an AIFF file?

It is Apple's uncompressed audio format, similar in size to WAV. It keeps the sound exactly as it was recorded.

How big is an hour of AIFF?

CD quality stereo takes about 10.6 MB a minute, so an hour is over 600 MB. Mono at a lower rate is much smaller.

Can the bot read an .aif file?

Send it as an audio file or as a document. The shorter .aif extension names the same format as .aiff.

Is AIFF better than WAV for transcription?

No, they carry the same kind of uncompressed sound. A clear voice and little noise matter more.

What if my AIFF is larger than 2 GB?

Cut it into parts or save a smaller mono copy, since files above 2 GB are not accepted.

Sources

Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.

  1. Audio Interchange File Format (Wikipedia), Wikipedia · checked
  2. WAV (Wikipedia), Wikipedia · checked
  3. Bit rate (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