Transcribe audio to text

Upload an interview, lecture or meeting recording and get an accurate transcript back.

or drop them here

Up to 100 MB · 5 files at once

Tool settings

Processed on our own servers, never sent to a third-party service. Files are deleted automatically after two hours, and you can delete them sooner from the result screen.

How to transcribe audio to text

  1. Upload your audio file.
  2. Pick the language, or let it detect one.
  3. Download the transcript as text, DOCX or SRT.

Timestamps and speakers

The transcript is segmented by time and, where voices are distinct, separated by speaker.

Subtitle formats too

Export SRT or VTT if the transcript is destined for video.

Runs on our hardware

Transcription happens on our own servers. Your recordings are not sent to a third-party speech API.

Processed on our own servers

Nothing is passed to a third-party API. Files are deleted automatically two hours after upload.

Questions

How accurate is it?

On clear audio with one or two speakers, typically well above 90%. Background noise, heavy accents and people talking over each other all reduce accuracy.

How long can the recording be?

Up to about two hours per file. Processing takes roughly a tenth of the recording length.

How long are my files kept?

Two hours, then they are deleted automatically. You can also delete them immediately from the result screen.

Is there a watermark?

No. What you download is exactly what the tool produced.