I'm trying to find specific information on how Apple transfers & stores the voice data that's transferred for speech recognition in Safari as part of WebSpeechAPI. All I keep seeing are generic privacy documents that do not provide any detail. Is anyone able to point me in the right direction of an explanation of how customer data is used?
Replies
Safari now supports WebSpeechAPI in the latest version. It's listed on the Safari release notes. Personally I'm using react-speech-recognition npm package which works in both Chrome and Safari. Caveat is you need to have Siri enabled on your Mac/Phone.
Posted
by
Share this post
Copied to Clipboard
-
Do you know if this is the on device speech or the cloud version? I would assume the former to avoid limitations.
-
EDIT: It seems somewhat buggy. Oftentimes a speech result will contain a duplicate of itself concatenated:
Speak "This is a test" -> result -> "This is a test This is a test."
-
There is no on-device speech recognition. All of it is done through Siri. That's why I'm looking to hear from someone from Apple on how that data is stored/used.
—
-
—
KTRosenberg
-
—
antonpug
Add a CommentSide-note: how were you able to get it to work in the first place? I am running a localhost python3 server to test and I can't get the page to request access to the microphone in Safari--only in Chrome.
Safari now supports WebSpeechAPI in the latest version. It's listed on the Safari release notes. Personally I'm using react-speech-recognition npm package which works in both Chrome and Safari. Caveat is you need to have Siri enabled on your Mac/Phone.