Skip to main content
Aivently
Log inGet started
Menu

Transcribe audio and video to editable timed text.

Upload supported audio or video, review the measured credit quote, then check the transcript in the editor. Correct words and timing before exporting your result. Your first 10 minutes are free once your email is verified.

interview-take-2.mp4timed cues ready for review

Start with the file you have

An existing subtitle file already contains text and timing. A recording needs transcription to turn speech into timed text first.

Accepted media

Common audio and video containers are inspected before quote. Only the languages and audio tracks available for your file are shown.

  • AUDIO
    MP3WAVM4AAACFLACOGGOPUSWMAAIFFAMR
  • VIDEO
    MP4/M4VMOVMKVWebMAVIMPEGTS/MTSWMVFLV

How it works

Nothing is charged until you approve the quote.

  1. 01

    Add audio or video

    Upload a supported recording. Its audio track, encoding and duration are checked before the quote.

  2. 02

    Review the quote

    Pick the language and see the exact credit cost.

  3. 03

    Edit and export

    Review the result, make changes, and download it.

From a recording to the right export

Upload your audio or video file when the words are still in the recording. Check the available processing choices and exact quote, then review the timed transcript against the original audio before exporting.

Need subtitles with timing?

Choose an available SRT, VTT or ASS export for captions that need start and end times. Confirm what your destination accepts, then check cue boundaries, names and numbers during playback.

Check formats

Need text for reading or reuse?

TXT is plain text: it leaves out subtitle timing and cannot carry a timed caption track on its own. JSON is a structured export for further processing; check the available formats for your result.

Common questions

Can I transcribe an MP3 or MP4?

Supported audio and video files are inspected before quoting. An MP3 or MP4 extension alone does not guarantee support: encoding and an available audio track matter. Files must fit both the 4 GB and 3 hour limits.

Which spoken languages can I use?

The workflow shows available language choices for your file. Check those choices before confirming the measured quote; availability can differ from subtitle translation.

Can I edit and export the transcript?

Review the timed cues in the editor, correct words and timing, and wait for changes to save. Choose an export format available for the result; not every format is available for every job.

How does a job work?

Add a supported file, review the measured quote, and confirm. Nothing runs — and no credits are reserved — until you approve the quote. Progress appears on your dashboard and finished results land in Projects.

How long are results kept?

Results stay in Projects until you delete them. Original media is removed 24 hours after a successful job; failed uploads are removed after 7 days.

How does the editor save?

Every cue edit saves automatically with a version number. The save state in the toolbar always shows whether the latest change is stored.

What happens if a job fails?

Credits reserved for work that was not delivered are returned to your balance automatically. You pay only for delivered work.

Turn your next recording into timed text

Upload, confirm the quote, and review before export.

Support