Format

AAC audio to text

An AAC file is one of the ten containers the upload field names, so it goes up as it is. The words come back line by line, each with the second it starts and the second it ends. One file is up to 64 MB and 120 minutes, the free plan is $0, Pro is $10 a month.

Updated 2026-10-25 · Author: Mark Burmistrov · 4 minutes

Two ways an AAC file reaches you

AAC is a codec, and a codec travels inside a container. When a phone or a voice recorder writes an .aac file, the audio is often a bare stream; when a video tool writes one, the same audio sits inside an MP4 box. Both cases end up here, and the only difference is what you call the file on your disk.

The two shapes an AAC recording takes
What you have on diskWhat to doWhy
A raw .aac file upload it unchanged aac is named in the accept list of the upload field
AAC inside an MP4 container, saved as .m4a upload it unchanged m4a is named in the accept list of the upload field
AAC inside an MP4 container, saved as .mp4 upload it unchanged mp4 is named in the accept list of the upload field
AAC inside a container with an unusual name rename the copy to .m4a and upload that the picker filters by extension and by the type the system reports

What the limits mean for an AAC file

AAC files against the plan limits
LimitValueSource
Size of one file 64 MB transcrib.si/pricing.html, checked
Length of one file on Pro 120 minutes transcrib.si/pricing.html, checked
Length of one file on the free plan 30 minutes transcrib.si/pricing.html, checked
Files a day on the free plan 3 transcrib.si/pricing.html, checked
Free plan price $0 transcrib.si/pricing.html, checked
Pro price $10 a month paid yearly ($120 a year), or $20 a month paid monthly transcrib.si/pricing.html, checked
Audio covered by Pro a month 1,500 minutes of fair use transcrib.si/pricing.html, checked

Speakers, timecodes and exports

Switch on “Split by speaker” and the lines are grouped by voice — the same request that the speaker labels page compares across seven services. Every line keeps its timecodes, so the text can be lined up against the recording or exported as subtitles in SRT or VTT. Plain text is TXT or Markdown, tabular output is CSV, and DOCX is there on Pro. The meeting guide shows how to use all of it on one recording.

Where the recording is read

An AAC file in Russian is processed on our own transcription infrastructure, outside the United States. A file that is entirely in English can be passed to a third-party cloud speech provider in the United States when that fallback is enabled. The audio is used to produce the transcript and to run the service; it is never sold and never used to train models for other customers. Deleting the transcript deletes the audio with it, and the file leaves the live system immediately and the encrypted backups within 30 days. The privacy policy and the security notes spell this out.

Two languages, one file. Russian and English are recognized, and a recording that mixes them is recognized as a mix. Set the language yourself or leave it on automatic detection.

If the upload is refused

  • The file is over 64 MB. AAC is a compressed format, so this usually means a very long recording. Split it, or move to the guide for long recordings.
  • The free plan says the file is too long. Free accepts up to 30 minutes; Pro takes files up to 120 minutes.
  • The picker does not show your file. Rename a copy to .m4a or .mp4 and try again — both are in the accept list.
  • The sound is broken. A recording cut short stays cut short; no service can invent the missing end of it.

The other containers

The upload field of the site names ten of them: mp3, wav, m4a, mp4, webm, ogg, flac, aac, wma and mov. All of them go through one pipeline and return the same structure, so an AAC recording and an MP3 of the same hour give the same text. The general guide lists every format with the limits next to them.

Try it now

Put a file on the page and read the first lines.

The widget below is the same one as on the home page: file → transcript with timecodes and speakers → export. The transcript is saved to your account.

Drop an audio or video file

or — mp3, wav, m4a, mp4, up to 64 MB and two hours

No account yet? The free plan needs no card. Create a free account or sign in.

FAQ

Questions this page answers.

Is a raw .aac file accepted?

Yes. The upload field of the site names aac among the ten containers it takes, and the file is read exactly as it was written.

My AAC file is really an MP4 with a wrong name. What do I do?

Make a copy and name it .m4a or .mp4. Both extensions are in the accept list, so the picker will show the file and the server will read the container as it is.

How long can an AAC recording be?

Up to 120 minutes and 64 MB per file on Pro and Team. The free plan takes files up to 30 minutes and 3 files a day.

Can the speakers be told apart?

Yes, and on every plan. Tick “Split by speaker” and the lines are marked with the voice they belong to, exactly like on the MOV page.

Do you publish an accuracy number?

No. The site publishes no single accuracy figure — ask for the evaluation report and the sample set and we will send them.

Keep reading

Related pages.

MOV to text

The picture is ignored, the sound is not.

WMA to text

A Windows recording, uploaded as it is.

Voice memos

Where most AAC recordings come from.

Russian audio

The Russian path through our engine.

Accuracy compared

What six services publish about their own numbers.

Pricing

The plans and the limits.

Written by a person

Mark Burmistrov, Founder.

Every number on this page comes from the service contract, the pricing page or our own measurements. The author of the page and the publisher of the site are the same person. Questions and corrections: support@transcrib.si.