Voice notes

WhatsApp voice messages to text

A three-minute voice note you cannot listen to right now becomes a paragraph you can read in ten seconds.

The short answerTo turn a WhatsApp voice message into text, export it from the chat (long-press the message, then Share or Forward to save it as a file) and upload it to SpeakToWords. WhatsApp voice notes are OPUS audio, which is accepted directly; the text comes back punctuated within a minute or two.
Transcribe a file free See plans 15 free minutes, no card. 50+ languages. Files up to 500 MB.

How it works

  1. Export the voice noteLong-press it, Share, then save to Files (iPhone) or share to your browser (Android).
  2. Upload itThe .opus or .ogg file goes in as it is - no conversion.
  3. Read itPunctuated text, ready to copy into a reply.

WhatsApp has its own transcripts now - why use this?

WhatsApp can transcribe voice messages on some phones and in some languages, on the device. It is handy when it is there. Use a file transcription when it is not offered for your language, when the note is long, when you need to keep or edit the text, or when you have a batch of notes to go through.

Telegram and other apps

Telegram, Signal and Viber voice messages export the same way and are accepted as OPUS, OGG, M4A or AMR.

Pricing

A free account transcribes 15 minutes with no card and shows the opening of each transcript; the full text unlocks with the 7-day trial or a plan from €9.99 a month for 500 minutes (€4.00 for 3 months until 6 December).

Questions

Is it free?

A free account transcribes 15 minutes with no card and shows the opening of each transcript; the full text unlocks with the 7-day trial or a plan from €9.99 a month for 500 minutes (€4.00 for 3 months until 6 December).

How accurate is it?

On clear speech, upwards of 99% of words come back right, punctuated and with a timestamp on every line. Background music, people talking over each other, strong accents and unusual names cost accuracy; the editor plays the audio from any line so you can fix those quickly.

Does it label who is speaking?

Not yet. Every line carries the second it was said, so you can jump to it and listen, and add names in the editor. If speaker labels are essential, see the comparison pages for tools that offer them.

What happens to my file?

It is processed for you only, encrypted in transit, and never used to train anything.

Related

Try it on your own recording

A free account transcribes 15 minutes with no card and shows the opening of each transcript; the full text unlocks with the 7-day trial or a plan from €9.99 a month for 500 minutes (€4.00 for 3 months until 6 December).

Start free