Free · No sign-up · Nothing uploaded

Free Audio & Video to Text Converter: Private, In Your Browser

Get the words as plain text you can copy or download.

How to turn audio or video into text

  1. Choose your file. MP4, MOV, MP3, M4A, WAV, OGG and WebM all work, up to 60 minutes on a computer and 15 minutes on a phone.
  2. Pick the spoken language. Auto-detect works, but choosing the language gives better results, especially for short clips. For languages other than English, Accurate is chosen for you on a computer.
  3. Press Transcribe for free. Your browser listens to the file on your device. The first time, it downloads the free speech model once; after that it starts right away.
  4. Read and fix the text right in the box, then Copy it or Download TXT.

Plain text or a subtitle file?

This tool gives you the words as one block of text, ready to quote, search or turn into notes. If you need each line with its start and end time, for YouTube or a video editor, make a subtitle file instead. If you only want to type with your voice, use voice typing.

Tips for a better transcript

Our guide to transcribing audio for free without uploading has more detail on each setting.

Private and free

The speech recognition runs in your browser, so your recording never leaves your device. There's no account, no limit on how many files you transcribe, and nothing to install.

Questions

Is the audio to text converter free?

Yes. It runs on your own device, so there's no cost, no sign-up and no limit on the number of files.

Is my file uploaded?

No. Your browser reads the file and turns the speech into text on your device. Nothing is sent to Spokly.

Which languages can it transcribe?

33 languages, including Arabic, English, French, Spanish, German, Turkish, Hindi, Urdu and Indonesian. Choose the spoken language for the best result.

How long can my file be?

Up to 60 minutes on a computer and 15 minutes on a phone. For a longer recording, split it into parts and transcribe each one.

Can I get timestamps?

This tool gives plain text. For a timed version, use the Subtitle file tool: it makes an SRT or VTT file with a start and end time for every line.