This browser is no longer supported.
Upgrade to Microsoft Edge to take advantage of the latest features, security updates, and technical support.
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(179.20000000000002, 63%, 27%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EJ%3C/text%3E%3C/svg%3E)
does Microsoft Speech Platform -- ISpRecoContext [Microsoft Speech Platform Microsoft Speech Platform Native Code API] perform better?
i am using the windows crate with rust -- for the following. it seems like there is some lag with that api for Windows.Media.SpeechRecognition
the "voice access" app has similar lag too during dictation. but it is NOT known what API it's using: Windows.Media.SpeechRecognition???
F.Y.I. i am NOT interested in the 100% cloud api but would possibly try out the win32 -- ISpRecoContext
does another local/offline 'api' have less lag than: Windows.Media.SpeechRecognition? am open to an MacOS Apple solution as i've already done some research and investigation into that but the "cost of entry" for current hardware is like 4 times higher!!!
i have limited experience with -- win32 api. however was learning Swift for MacOs
ISpRecoContext is not a win32 api. There is no winapi to realize speech recognition. And now the latest supported speech solutions are in the Azure Cognitive Services for Speech.
okay. i'm gonna try out the free local/offline open-ai 'whisper' speech recognition as well as possibly 'vosk' all for free. you do realize that the Web Speech API inside Google Chrome does seem to have "less lag" -- than my experience with Microsoft "voice access" as well as what i threw together with the Rust language 'windows' crate that's on Windows.Media.SpeechRecognition. b.t.w. some of these cloud api's charge $500 a month. have had issues before with internet access
ISpRecoContext is not a win32 api. There is no winapi to realize speech recognition.
It is SAPI : https://learn.microsoft.com/en-us/previous-versions/windows/desktop/ms720151(v=vs.85)#api-for-speech-recognition
I tested MS SAPI samples like DictationPad and I don't see particular lag