Audio to Text

Upload a recording and download a transcript to read, search, edit and share.

Uploading opens soon.

Audio or video up to 2 hours and 2 GB.

MP3, M4A, AAC, WAV, OGG, FLAC, WebM, MP4, MOV and MKV

Any recording with speech in it

SimpleTranscribe listens to your recording and writes down what was said, in any of 100 languages. Use it for interviews, podcasts, meetings, talks and voice memos.

Download the transcript as plain text (TXT) or a Word document (DOCX), with or without timestamps. For subtitles, choose SRT or VTT. It's free, with no sign-up.

How it works

  1. Choose your recording

    Pick an audio file, such as an MP3, M4A or WAV, up to 2 hours long.

  2. We transcribe it

    Your file goes up over an encrypted connection, and the speech in it is turned into text.

  3. Download your transcript

    Save it as TXT or DOCX to read and edit, or as SRT or VTT subtitles. It's erased 24 hours after it's ready.

A real transcript

This is the TXT download, with timestamps. Automatic transcripts aren't perfect: parts can come out without capitals or punctuation, and words can be missed, so check anything important.

transcript-2026-11-09-19b8d475.txt 
[00:00:00] ozymandias of egypt i met a traveller from an antique land who said two vast and trunkless legs of stone stand in the desert near them on the sand half sunk a shattered visage lies whose frown and wrinkled lip and sneer of cold command tell that its sculptor well those passions read which yet survive stamped on these lifeless things the hand that mocked them and the heart that fed and on the pedestal these words appear my name is ozymandias king of kings look on my works ye mighty and despair nothing beside remains Round the decay of that colossal wreck, Boundless and bare, the lone and level sands stretch far away.

Transcribed free with SimpleTranscribe.com

The whole recording, unedited (0:00–1:01).

“Ozymandias of Egypt” by Percy Bysshe Shelley, read by Karen Savage for LibriVox, in the public domain. Listen to the recording on archive.org

A clear recording of one reader: background noise, distance from the microphone and several voices give more errors.

Tips for your recording

  • Record close to the person speaking. A phone near the speaker picks up far more than a microphone across the room.
  • Keep background noise down: music, traffic and other conversations make words harder to recognize.
  • Ask people to take turns: when they talk over each other, the overlapping words are the ones most likely to be missed.
  • Upload the original recording, not a copy played through a speaker and recorded again: each copy loses detail.
  • Longer than 2 hours? Split the recording into parts and upload each one.

Formats, limits and privacy

Supported formats

Audio
  • MP3
  • M4A
  • AAC
  • WAV
  • OGG
  • FLAC
  • WebM
Video
  • MP4
  • MOV
  • WebM
  • MKV

Recorded a video instead? Upload it here, or use Video to Text: the speech in it is transcribed the same way.

Limits

Length
Up to 2 hours per file
Size
Up to 2 GB per file
Each day
Up to 4 hours of audio, with no sign-up
Languages
100, detected automatically

Privacy

  • Your audio is deleted as soon as its transcript is done, or if transcription fails.
  • Your transcript is erased 24 hours after it's ready, so download it soon.
  • Files whose upload is never finished, or whose transcription is never started, are deleted automatically.

Questions about audio to text

Is it really free?

Yes. There's no sign-up and nothing to pay. You can transcribe up to 4 hours of audio a day, in files of up to 2 hours each.

Can I edit the transcript?

Yes, once you've downloaded it. Open the Word file (DOCX) in a word processor, or the TXT in any text editor, to fix names, add headings or cut what you don't need.

Does the transcript say who is speaking?

No. It doesn't label speakers. A new paragraph starts after a pause, or once a paragraph gets long, not when someone else starts talking. For an interview or a meeting, download the Word file (DOCX) with timestamps and add the names as you read. Each paragraph's timestamp shows where it is in the recording.

How accurate is it?

It depends on the recording and on its language. Clear speech close to the microphone comes out best; noise, music, people talking at once and strong accents make mistakes more likely. SimpleTranscribe uses OpenAI's open-source Whisper speech recognition models. Check names, numbers, technical terms and anything important before you rely on the text.

Which languages does it understand?

Speech in 100 languages. The language is detected automatically from the first part of the recording, so each file should be in a single language. Accuracy varies by language. For English text from a recording in another language, use Translate Audio to English.

Transcribe something else