# Practicing example WK sentences (speach-to-text recognition tool) **URL:** \ **Category:** Speaking\ **Created:** [January 22, 2026, 8:18am UTC](https://community.wanikani.com/t/practicing-example-wk-sentences-speach-to-text-recognition-tool/73331 "2026-01-22T08:18:51Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![wojtek](https://sea1.discourse-cdn.com/wanikanicommunity/user_avatar/community.wanikani.com/wojtek/32/742193_2.png) [@wojtek](https://community.wanikani.com/u/wojtek)\ **Post date:** [January 22, 2026, 8:18am UTC](https://community.wanikani.com/t/practicing-example-wk-sentences-speach-to-text-recognition-tool/73331/1 "2026-01-22T08:18:51Z")
Hi, when studying (doing lessons) I try to read all example patterns of use and example sentences (turns out it GREATLY improve the retention :D). However, while it may _sound_ OK-ish for me I’m looking for something that would either record and compare it with the example or transcribe-back what I said so I could compare if at least “the computer” understood. For all such voice interactions on my computer I’m using Handy ([GitHub - cjpais/Handy: A free, open source, and extensible speech-to-text application that works completely offline.](https://github.com/cjpais/handy); with `Parakeet V3` model) and it works wonderful… but only for english/spanish/polish as it doesn’t seem to support Japanese ☹ Any suggestion how to do handle that? or user-script? (I know there is one for voice input reviews but it’s only for vocabulary) ---
**Author:** ![gijsc1](https://sea1.discourse-cdn.com/wanikanicommunity/user_avatar/community.wanikani.com/gijsc1/32/529710_2.png) [@gijsc1](https://community.wanikani.com/u/gijsc1)\ **Post date:** [January 22, 2026, 12:41pm UTC](https://community.wanikani.com/t/practicing-example-wk-sentences-speach-to-text-recognition-tool/73331/2 "2026-01-22T12:41:38Z")
I don’t know exactly how it is implemented, but there is already a [voice input script](https://community.wanikani.com/t/userscript-voice-input-using-web-speech-api/62368/61) for doing regular reviews. I haven’t used it in a while, but it used to work great for anything longer than one or two syllables. You could look at the implementation or ask the creator for advice. For a more low tech option, if you just want to check if your output is parsable without doing anything with the result, you could try to use the voice input mode of google translate. Windows, and I assume most other operating systems as well, also comes with a [build in speech to text application](https://support.microsoft.com/en-us/windows/use-voice-typing-to-talk-instead-of-type-on-your-pc-fec94565-c4bd-329d-e59a-af033fa5689f) which you could use to transcribe what you are saying to any textbox. ---
**Author:** ![wojtek](https://sea1.discourse-cdn.com/wanikanicommunity/user_avatar/community.wanikani.com/wojtek/32/742193_2.png) [@wojtek](https://community.wanikani.com/u/wojtek)\ **Post date:** [January 23, 2026, 8:12am UTC](https://community.wanikani.com/t/practicing-example-wk-sentences-speach-to-text-recognition-tool/73331/3 "2026-01-23T08:12:19Z")
> [@gijsc1](#): > > I don’t know exactly how it is implemented, but there is already a [voice input script](https://community.wanikani.com/t/userscript-voice-input-using-web-speech-api/62368/61) for doing regular reviews. I haven’t used it in a while, but it used to work great for anything longer than one or two syllables. You could look at the implementation or ask the creator for advice. Yes, this is the script I mentioned but it looks like it only works with the main item ☹ > [@gijsc1](#): > > For a more low tech option, if you just want to **check if your output is parsable without doing anything with the result** , you could try to use the voice input mode of google translate. Yes, this is what I’m looking for basically and what said Handy is doing 🙂 But would love to have something build-in (script in WK) or readily available (like Handy, which basically runs constantly in the background and I have a quick shortcut, and then it basically outputs what I said; yes, basically I dictated most of this reply with handy 😃 ) ---
**Author:** ![polv](https://sea1.discourse-cdn.com/wanikanicommunity/user_avatar/community.wanikani.com/polv/32/572691_2.png) [@polv](https://community.wanikani.com/u/polv)\ **Post date:** [January 23, 2026, 8:46am UTC](https://community.wanikani.com/t/practicing-example-wk-sentences-speach-to-text-recognition-tool/73331/4 "2026-01-23T08:46:53Z")
Reading aloud on a smartphone with voice typing? Depending on the keyboard, it might not need to be online. Windows text-to-speech (Win+H) might work just similarly. Otherwise, on a PC, some browsers may support [SpeechRecognition](https://developer.mozilla.org/en-US/docs/Web/API/SpeechRecognition) API – [Demo](https://developer.chrome.com/blog/voice-driven-web-apps-introduction-to-the-web-speech-api) ---
**Author:** ![wojtek](https://sea1.discourse-cdn.com/wanikanicommunity/user_avatar/community.wanikani.com/wojtek/32/742193_2.png) [@wojtek](https://community.wanikani.com/u/wojtek)\ **Post date:** [January 23, 2026, 10:21am UTC](https://community.wanikani.com/t/practicing-example-wk-sentences-speach-to-text-recognition-tool/73331/5 "2026-01-23T10:21:54Z")
> [@polv](#): > > Reading aloud on a smartphone with voice typing? Depending on the keyboard, it might not need to be online. Yeah, I was doing that with Microsoft translate but it’s a bit cumbersome and disrupts a bit study flow (also, I try to avoid having a phone near me to avoid distractions ☹ ) > [@polv](#): > > Windows text-to-speech (Win+H) might work just similarly. I’m on macOS and it’s text-to-speech is absurdly terrible (hence using external tool) > [@polv](#): > > Otherwise, on a PC, some browsers may support [SpeechRecognition](https://developer.mozilla.org/en-US/docs/Web/API/SpeechRecognition) API – [Demo](https://developer.chrome.com/blog/voice-driven-web-apps-introduction-to-the-web-speech-api) Despite it’s being on MDN it’s not supported by Firefox ☹ ![image](https://global.discourse-cdn.com/wanikanicommunity/original/4X/6/f/5/6f580d3d0203359064c7e19d99d0d3fbb0101168.png) ([1456885 - Not able to use Voice for Google Docs Integration due to missing SpeechRecognition support](https://bugzilla.mozilla.org/show_bug.cgi?id=1456885), [1856507 - Sites breaking due to missing SpeechRecognition support](https://bugzilla.mozilla.org/show_bug.cgi?id=1856507)) * * * So yeah, to narrow it down: something multiplatform (with macOS support), working on computer or in a browser but not relying on SpeechRecognition API… Maybe a LLM model that I could ask to be added to Handy? ---
**Author:** ![s1212z](https://sea1.discourse-cdn.com/wanikanicommunity/user_avatar/community.wanikani.com/s1212z/32/182211_2.png) [@s1212z](https://community.wanikani.com/u/s1212z)\ **Post date:** [January 23, 2026, 1:50pm UTC](https://community.wanikani.com/t/practicing-example-wk-sentences-speach-to-text-recognition-tool/73331/6 "2026-01-23T13:50:04Z")
> [@wojtek](#): > > I’m on macOS and it’s text-to-speech is absurdly terrible (hence using external tool) I had made a STT deck for sentence shadowing and thought my iphone was a decent threshold for clean pronunciation and used it for text input (though they were common phrases). The only issue I’ve heard from native users is that when they have thick dialects, it tends to break. My understanding is STT has some context dependency and many WK sentences are intentionally absurd, though one would think common collocations should be ok (never tried it myself)….might be a good experiment if you know a native speaker for STT on the WK sentences and see what they get. ---
**Author:** ![wojtek](https://sea1.discourse-cdn.com/wanikanicommunity/user_avatar/community.wanikani.com/wojtek/32/742193_2.png) [@wojtek](https://community.wanikani.com/u/wojtek)\ **Post date:** [January 23, 2026, 3:07pm UTC](https://community.wanikani.com/t/practicing-example-wk-sentences-speach-to-text-recognition-tool/73331/7 "2026-01-23T15:07:05Z")
Hmm… that’s interesting. Though, suprising as it may be, I’m not sure macOS and iOS use the same tech for STT 🤔