AnkiWeb addon 499865194
Reads card fronts aloud, listens for spoken answers ended with "done," then reveals the back and automatically grades recall using Google Gemini AI, hands-free.
Open on AnkiWeb GitHub Find alternatives
active
| Min Anki | Max Anki | Updated |
|---|---|---|
| 25.09 | + | 2026-08-03 |
Loading…
Enables fully hands-free Anki review by reading cards aloud, recognizing spoken answers, and scoring them with AI, OCR, and multi-language support.
Enables fully offline, hands-free deck review using spoken commands to reveal answers, grade cards, and undo actions, with configurable vocabulary, timing, and noise filtering.
Lets you answer flashcards by typing, speaking, or handwriting, then has a chosen LLM grade the answer as correct, partly, or totally wrong and explain mistakes.
Exports Anki cards to interactive, searchable, printable HTML pages rendered by Anki's engine, with live browsing, narrated slideshows, rapid presentations, filtering, media support and study tools.
Enables keyboard-driven Anki reviewing with hjkl answer keys, front-side grading, configurable shortcuts, hidden or disabled buttons, Pass-Fail mode, answer color coding, zoom controls, and last-grade display.
Reads flashcard text aloud offline with customizable voices, speeds, keyboard shortcuts, smart cloze handling, and over 150 built-in medical pronunciation corrections.
Review your cards hands-free, graded by AI.
Voice Review reads each card's front out loud, listens to your spoken answer, and when you say "done" it shows the back and grades you automatically. For every card: the front is read aloud, you say the answer, you say "done", the back appears, and the matching button (Again / Hard / Good / Easy) is pressed for you based on how well you recalled it.
Great for studying while your hands or eyes are busy.
What you need
First run
The add-on downloads about 60 MB of speech files once, then a welcome window helps you paste and test your free key. After that, just start reviewing.
Controls
Privacy
Detecting the word "done" runs entirely on your computer. When you finish an answer, the audio of that answer and the card's back are sent to Google's Gemini API for grading, and nothing else. On the free tier, Google may use submitted content to improve their products. You can switch to a fully local mode in the settings, though grading is less accurate with uncommon words like technical or medical terms.
Uninstalling
Voice Review loads native speech libraries while Anki runs. To remove it, close Anki, restart it while holding the Shift key (which starts with add-ons off), then delete it from Tools > Add-ons.
Source code and support
https://github.com/ArnieFTC/anki-voice-review
Please report problems on the GitHub issues page.
Review your Anki cards hands-free. Voice Review reads each card's front out loud, listens to your spoken answer, and when you say "done" it shows the back and grades you automatically with Google's Gemini AI.
The loop for every card:
front is read aloud → you say the answer → you say "done" → the back is revealed → the AI grades what you said → the matching button (Again / Hard / Good / Easy) is pressed for you.
Your microphone is processed on your own computer. Only the audio of your spoken answer and the card's back are sent to Google for grading.
Install it from AnkiWeb: https://ankiweb.net/shared/info/499865194
In Anki, go to Tools → Add-ons → Get Add-ons and paste the code 499865194.
The first time it starts, it downloads about 60 MB of speech files (this happens once, and the files survive future updates). Then a welcome window helps you set up your free Gemini key.
Just start reviewing. Voice Review reads the front, then listens. Say your answer, then say "done", and it handles the rest.
Everything is in Tools → Voice Review Settings:
Speech recognition of the trigger word runs locally on your computer. When you finish an answer, the audio of that answer plus the card's back are sent to Google's Gemini API for grading. Nothing else is uploaded. On Google's free tier, submitted content may be used by Google to improve their products; you can turn off sending audio in the settings to keep it fully local (grading then relies on the local transcript, which is less accurate).
Voice Review loads native speech libraries while Anki runs, and Windows will not delete files that are in use. To remove it cleanly:
scripts/build_addon.py builds the installable voice_review.ankiaddon.scripts/build_assets.py builds the anki_tts_assets.zip (the speech library
and model) that is hosted on the GitHub release and downloaded on first run.MIT. See LICENSE.