Skip to content
Neattrim

Bulk transcribe audio

Queue many recordings, get one text file per recording and download them all together as a ZIP.

Runs on your device by default. Cloud mode, if you choose it, uploads your file to our servers. Uploads and results are deleted from our servers after 24 hours.

Preset for this page

Batch first
Yes
Outputs
TXT
Zip
Yes

The tool below starts with these settings. Change any of them in the tool.

Runs on your device. Your recording stays here.

Choose audio or videoClick, drop, or paste a recording. Device limits depend on available memory.

How to

  1. Add every recording. Select the whole folder of audio files and drop them onto the page together; they join the queue in order.
  2. Keep the text output. Leave the output as plain text, one .txt per file, which is this page's default and keeps the batch easy to search.
  3. Let the queue run. Start and leave the tab open. The files are transcribed one after another on your device.
  4. Download the ZIP. When the queue finishes, download one ZIP containing every transcript, named after its audio file.

Many files, one download

Transcribing one recording is easy; transcribing eighty is a chore if each needs its own upload and download. Researchers with interview sets, teachers with lecture archives, journalists with a folder of voice memos and call-centre reviewers all hit this. Here batch is the first-class mode: you add the whole set, the page processes the queue and returns every transcript in a single ZIP.

The output is plain text, one file per recording, named to match the audio, so you can search across the folder with any text tool. Accuracy varies per file, so a noisy recording will not match a clean one, and it is worth spot-checking a few. The batch runs on your device, one file at a time, so a big set takes time and memory. For a single recording with timestamps, use the meeting transcript or MP3 to text pages.

Frequently asked questions

How many files can I queue?
As many as your device can handle in one session. Very large sets are better split into several runs, so a single browser tab does not hold everything.
What is inside the ZIP?
One text file per audio file, named after the original recording, so you can match each transcript to its source easily.
Can I get timestamps or subtitle files in bulk?
This page defaults to plain text. For timestamps on a single file, use the meeting transcript page, which keeps timing and paragraphs.
Do the recordings leave my device?
Not by default. Each file is transcribed locally in turn, so a folder of private interviews stays on your computer.

More tools

All tools