Just say it.
Tap the mic, talk normally, and watch it turn into text. No signup, no time limit, and nothing is uploaded.
Runs on your machine · Your voice never leaves this device
Tap the mic and start talking.
Vraags
Is my voice uploaded anywhere?
No. The speech recognition model is downloaded to your browser the first time you use the tool, and everything after that runs on your own machine. Your microphone audio never leaves the device, and there is no server for it to be sent to.
Why is there a wait the first time?
The tool downloads a small speech recognition model (roughly 80MB) before the first transcription. Your browser caches it, so every later visit starts instantly and works offline.
How is this different from the Yaps app?
This page only types into itself. Yaps runs system-wide, so you hold one key and speak into any app you already use: your editor, your email, Slack, a document. It also cleans up filler words and punctuation as you go, and works offline once installed.
Which languages does it handle?
The balanced model is multilingual and handles most major languages automatically. The fast model is English-only but downloads in about half the time.
Does it work on a phone?
It runs in mobile browsers, but the model download and on-device processing are noticeably slower than on a laptop. On Android, the Yaps keyboard is a much better experience.
Now do it everywhere.
One key, any app, cleaned up as you speak.
Vereist macOS 13,0+ (Apple Silicon aanbevolen)