WhatsApp voice message to text
Read it instead of listening to it, without sending it to anyone.
Drop files here
or click to choose from your deviceAccepted: MP3, M4A, AAC, WAV, OGG, OGA, OPUS, FLAC, WEBA, MP4, M4V, WEBM, MOV, MKV
Up to 3 files per runUp to 20 MB per file10 runs per dayRemove limits with Pro✓ Works offline
Your files stay on your device
This tool runs entirely in your browser. Nothing is uploaded, nothing is stored, and you can even turn off your internet connection before you start.
How it works
- Save the voice message as a file: in WhatsApp, press and hold it and share it (on an iPhone, Forward and then the share icon), to Files for example or in an email to yourself. It usually ends in .opus.
- Drop the file here. The language is set to English; change it for a message in another language.
- Select Transcribe. The first time, the speech model (about 80 MB for English) downloads once; after that a minute of message is read in well under a minute.
- Copy the transcript, or download it as a text file.
Frequently asked questions
- Doesn’t WhatsApp do this itself?
- On many phones, yes: WhatsApp shows transcripts of voice messages on the phone itself, in English on both Android and iPhone. This page is for the rest — a voice message already saved on a computer, one forwarded to you that you want to keep as text, a phone where the option is missing, a transcript you need as a file, or a message in one of the languages your phone does not offer.
- Is the message uploaded?
- No. A voice message is private, and usually somebody else sent it to you: putting it through a service would be passing it on. Here the model is downloaded to your browser and the file is read on your own device.
- Which files work?
- .opus and .ogg, as WhatsApp and Telegram save them, as well as M4A, MP3, WAV and videos. Whatever your browser can play, it can read here.
- How accurate is it?
- English is read by Whisper base, which got about 5 % of words wrong on clearly read English in our tests. Voice messages are often recorded outdoors, in wind or in a kitchen, which costs accuracy; if it comes out badly, try Remove background noise from audio first.
- Which languages?
- Nine: English, Japanese, German, French, Spanish, Portuguese, Italian, Korean and Turkish. The seven after English and Japanese use a larger model, about 250 MB the first time.
Made for a specific use
Related tools
❝ Japanese speech to text Japanese recordings and videos into a transcript and SRT subtitles, without the audio leaving your device. ♪ OGG to MP3 Including the voice notes that arrive as .opus. ≋ Remove background noise from audio Fans, hiss and hum taken out from under a voice. ❝ Meeting recording to minutes Who said it, when they said it, and the headings ready for what you decide it meant.