Speech to text API per-app limits

Hello to all kind developers out there,


I’m currently developing a audio-messaging app, for users to send short audio to each other.

To make the communication experience as smooth and natural as possible, we are using Speech Framework for transcribing user-input live.


Since this feature is high in demand for some of our users, we are worried about unexpected quotas and limits.


(1) We know that individual recordings should be less than one minute

(2) The answer here says about 1000 reqs/hour per device:

https://developer.apple.com/library/archive/qa/qa1951/_index.html#//apple_ref/doc/uid/DTS40017662


(3) The documentation says: “Individual devices may be limited in the number of recognitions that can be performed per day and an individual app may be throttled globally, based on the number of requests it makes per day”.


We are well under limits for (1) and (2), but there are no specific documentation for limits per-app, and being “throttled globally” sounds scary.

Can anyone give us information about per-app limits or any other kinds of limit that might potentially put an end to our lives?


Thank you

Up vote post of fkymy Down vote post of fkymy
3.5k views
Posted by
fkymy
Reply
Add a Comment

Replies

Hi, I'm also working on the Speech framework for speech recognition. Did u get any info on the same?
Posted by
vinothkanna
Up vote reply of vinothkanna Down vote reply of vinothkanna
Add a Comment

Hi, I'm looking for this answer as well.

What I found of use so far:

Be prepared to handle failures caused by speech recognition limits. Because speech recognition is a network-based service, limits are enforced so that the service can remain freely available to all apps. Individual devices may be limited in the number of recognitions that can be performed per day, and each app may be throttled globally based on the number of requests it makes per day. If a recognition request fails quickly (within a second or two of starting), check to see if the recognition service became unavailable. If it is, you may want to ask users to try again later.

Plan for a one-minute limit on audio duration. Speech recognition places a relatively high burden on battery life and network usage. To minimize this burden, the framework stops speech recognition tasks that last longer than one minute. This limit is similar to the one for keyboard-related dictation.

Source: https://developer.apple.com/documentation/speech/sfspeechrecognizer

Source: https://developer.apple.com/videos/play/wwdc2019/256/

Apple please elaborate "...may be throttled globally...". Will this apply also for on-device use or not?

Thank you

Posted by
Pagge
Up vote reply of Pagge Down vote reply of Pagge
Add a Comment