AAC to text from your original audio

Most raw .aac files come straight from a recording app or a device’s own voice recorder, before any editing app touches them. Hushscript turns the speech in that file into a transcript you can search, correct, and export. Start with the original .aac file: making an MP3 or WAV copy first adds a step but cannot restore detail that the AAC encoding no longer contains.

AAC transcription from the original file

AAC is a lossy audio codec, while .aac is commonly used for AAC audio in an ADTS container. An M4A takes a different route: it is an MPEG-4 container that can carry AAC audio. If your recording is actually an M4A file, use the M4A to text page instead. MDN’s audio codec guide lists AAC in both ADTS and MP4 containers, which is why two files with AAC audio can have different extensions and behave differently in a browser.

Use the file you received or recorded rather than renaming its extension. Hushscript inspects the media itself. In the full app, supported audio uploads unchanged; local preparation is used when the file needs it.

Preview AAC to text when your browser supports the file

The public preview transcribes up to 5 minutes before signup, but it deliberately uses the browser’s media decoder rather than the app’s broader fallback path. AAC support varies by browser, operating system, profile, and container. A compatible file can go straight through the preview. If the browser cannot decode it, the page offers the full app instead of claiming that every AAC file will preview.

The preview is a sample, not the full job: only its clip is sent. After you sign in, upload the source in the app to transcribe the complete recording.

Add context for the full AAC transcription

Names, abbreviations, and specialist terms are hard to infer from sound alone. For the full job, add one-off keyterms or a custom prompt, or reuse a saved dictionary and prompt preset. These choices guide transcription; they do not modify the AAC or improve its encoded sound.

You can also choose the source language, use automatic language detection, turn speaker detection on or off, and configure multichannel handling when separate voices occupy separate channels. Speaker detection is available across the supported transcription languages.

Edit and export the AAC transcript

When the transcript is ready, check names, numbers, and speaker labels against the recording, then correct words, rename or reassign speakers, merge or split turns, search, find and replace, undo, redo, and revert edits. The AAC remains the source; the transcript becomes the working document.

Export the result as a document, subtitle file, spreadsheet, structured data, or editor timeline. Hushscript provides 21 unwatermarked formats, so you can use the same transcript for reading, captioning, research, or editing.

AAC to text facts

Question	Hushscript
Input	The original .aac audio file
Browser preview	Up to 5 minutes when the browser can decode the AAC profile and container
Preview fallback	Continue in the full app if the public preview cannot decode the file
Recording length	Up to 10 hours
Languages	Roughly 99, with automatic detection
Speaker labels	Available across supported transcription languages
Full-job context	Keyterms, prompts, saved dictionaries, and saved prompt presets
Exports	21 formats with no watermark
Billing	Pay-as-you-go, no subscription

To convert AAC to text, upload the AAC itself. For broader guidance that applies to other recording formats too, see audio to text.

Updated: October 15, 2026