Audio to text

Upload a recording and get the text. An interview, a lecture, a call or a voice memo: transcription runs through a model that holds up against noise and accents.

Drag here or paste from the clipboard (Ctrl+V)

0 of 1 selected

mp3, m4a, wav, ogg, webm, flac — up to 50 MB. Drag it here or paste from the clipboard

If you transcribe regularly

A desktop app for transcribing and recording meetings

Konspekt for Windows records both sides of a call, transcribes it and writes a summary right on your computer — the recording never leaves it.

About Konspekt

What transcription is

Transcription turns spoken words into written text. What was said in a conversation, a lecture or an interview becomes a document you can search, quote and edit.

Upload a file and the model recognises the speech. Depending on the length and the quality of the sound it takes from a few seconds to a few minutes. Accuracy depends on the original recording: noise and overlapping voices hinder a model the same way they hinder a person.

Who needs it

  • Journalism: interviews and press conferences.
  • Education: lectures and seminars as text.
  • Law: hearings and witness statements.
  • Medicine: dictation and consultation records.
  • Business: meetings, webinars and presentations.
  • Video: subtitles and a text version of a clip.

Frequently asked questions

Which formats can I upload?

Ordinary recordings from a voice recorder, phone or call: mp3, m4a, wav, ogg and other common formats. The file must be audio: video is not accepted, so extract the sound track first.

How long does it take?

From a few seconds to a few minutes, depending on the length of the recording and how clean the audio is. A short note is transcribed almost instantly, an hour-long lecture takes noticeably longer.

How accurate is the recognition?

On a clean recording the accuracy is high. Noise, several people talking at once, a strong accent and a poor microphone all hurt it: in those cases reread the result and fix names and terms.

Is transcription free?

The first requests are free and need no sign-up. After that a daily limit applies, and if you need more you can top up your balance or take a package.

Does it tell speakers apart?

On this page the transcript comes as continuous text. If you need speaker labels and both sides of a call recorded, use Konspekt: it runs on your own computer and recognises voices.

What if the recording is confidential?

The file is sent to our service for transcription. If the recording must not leave your machine at all, use Konspekt: it transcribes locally and the audio never leaves your computer.