anki-miner 2.8.1

Automated Japanese vocabulary mining from media with Anki integration

Anki Miner

Turn native Japanese content into Anki vocabulary cards.

Please leave a ⭐ star if Anki Miner helped you - it helps others find it :).

Mining Demo

⬇️ Full demo with sound (MP4)

Example cards

⬇️ MP4 (sound)	⬇️ MP4 (sound)	⬇️ MP4 (sound)

Installation

Requirements

• ffmpeg only if installing from pip/pipx, .deb, or from source.
• alass (optional) for automatic subtitle retiming. Linux and Windows release builds bundle it. macOS users: brew install alass or place it on PATH.
• Anki with the AnkiConnect add-on. In Anki: Tools -> Add-ons -> Get Add-ons, paste code 2055492159, restart.

Download

Grab the download for your platform from the latest release:

Platform	Download
Windows	AnkiMiner-*-Setup.exe
macOS (Apple Silicon / M1-M4)	AnkiMiner-macOS-arm64.tar.gz
macOS (Intel)	AnkiMiner-macOS-x86_64.tar.gz ¹
Linux (Debian/Ubuntu)	anki-miner_*_amd64.deb
Linux (other)	AnkiMiner-*-Linux-x86_64.AppImage

¹ The Intel macOS build excludes local Whisper speech-to-text (Subtitles->Generate) and AVIF animated screenshots - every other feature works. For full functionality on an Intel Mac, install via pip instead: pipx install "anki-miner[asr]".

macOS first-run (unsigned binary): macOS Gatekeeper will block the app because it is not notarised. Extract the archive first, then clear the quarantine flag on the extracted folder (clearing it on the .tar.gz does not carry over to the extracted files):

xattr -dr com.apple.quarantine AnkiMiner/

Windows first-run (SmartScreen): Windows SmartScreen may show "Windows protected your PC". Click More info, then Run anyway.

Windows Defender false positive: Defender may wrongly flag the unsigned .exe (it bundles yt-dlp/ffmpeg, common AV triggers). Restore it from Protection history or report it to Microsoft.

Install from PyPI (Python 3.11+)

pipx install anki-miner   # or: pip install anki-miner

Install from source

git clone https://github.com/0xzerolight/anki_miner.git
cd anki_miner
pip install -e .

For full development setup, see CONTRIBUTING.md.

Tabs

• Video: mine video, in three sub-tabs. Single: one video/subtitle pair with word curation. Batch: a folder of episode/subtitle pairs for sequential processing — files are paired by episode number, so each folder / queue item should hold a single show (use Multi-Series Queue for mining multiple series at a time). YouTube: paste one or more URLs, then mine the queue.
• Deck Builder: point at a folder of episode/subtitle pairs and mine the full series into one named deck. Ranked by frequency; pick how many to include (all, top N, or a coverage target) and preview before cards are created.
• Audio: queue local audio + subtitle/transcript pairs (audiobooks, podcasts, radio, songs, lectures) and mine them audio-only; embedded cover art stands in for screenshots.
• Reading: mine manga and novels instead of video. Point at a mokuro-processed manga volume (an image folder or .cbz with its sibling .mokuro file) or a novel (.epub, or Aozora/plain .txt); cards carry the page image or the book cover. Anki Miner reads mokuro's output and does no OCR itself. Word curation works as in the other tabs.
• Analytics: history, series difficulty rankings, milestones, undo.
• Tools: generate subtitles from speech with a local Whisper model (no GPU required; optional CUDA/VAD packs install in-app), retime an out-of-sync subtitle file to your video with alass, or condense a video/audio file down to dialogue-only audio using its subtitles.
• Settings: Anki, Media, Dictionaries, Audio, Filtering, Frequency, Subtitles, YouTube, Themes. Saved to ~/.anki_miner/gui_config.json.

Other Features

• Extensive filtering options (i+1 filter, frequency limits, word blacklist, subtitle regex filtering, wordset filtering, per-volume minimum word occurrence, and more).
• Offline Yomitan dictionary import (definitions, pitch accent, frequency data) with priority ordering.
• Multiple frequency lists chained together, each indexed separately and ordered by priority.
• Expression (word-level) audio on cards from local audio packs, JapanesePod101, or Google Translate TTS (opt-in, chained).
• Per-dictionary glossary styling, Yomitan-style — each dictionary's own scoped CSS is applied automatically, self-contained per card.
• Subtitle timing preview with adjustable offset.
• Animated screenshots (see example card gifs).

Built-in themes (29)

• Ayu - Light, Mirage, Dark
• Catppuccin - Latte (light); Frappé, Macchiato, Mocha (dark)
• Dracula - Dracula, Alucard
• Everforest - Light, Dark
• GitHub - Light; Dark, Dark Dimmed
• Gruvbox - Light Medium, Dark Medium
• Kanagawa - Lotus (light), Wave (dark)
• Rosé Pine - Dawn (light); Main, Moon (dark)
• Solarized - Light, Dark
• Standalone - Light, Dark, Sakura, Nord, One Dark, Tokyo Night

Theme licenses: LICENSE-THEMES.md. Want another theme added? Suggest in a GitHub Issue.

How It Works

1. Read the subtitles and split Japanese into individual words.
2. Filter to content words you don't already know.
3. Grab a screenshot and audio clip from the video for each line.
4. Look up definitions in your configured offline dictionaries, optionally falling back to Jisho online if enabled (slower, rate-limited).
5. Send the finished cards to Anki.

Recommended Resources

Type	Resource	What you get	Download	Add via
Dictionary	Jitendex	JMdict successor; structured formatting, examples, tags	Yomitan zip	Add Dictionary…
Dictionary	JMdict	Plain glosses; smaller, faster to index	Yomitan zip	Add Dictionary…
Dictionary	Bee's Character Dictionary	Character names from your AniList/VNDB lists, with roles and descriptions	Generated on site	Add Dictionary…
Pitch	Kanjium	~124k patterns; drop-in TSV, no import step	TSV	Dictionary -> Pitch Accent File
Pitch	アクセント辞典v2	Richer NHK notation	Drive	Dictionary -> Pitch Accent File
Frequency	JPDB v2.2 Kana	All-round default for media	Yomitan zip	Filtering -> Frequency List File
Frequency	BCCWJ SUW+LUW	Balanced corpus; pairs well with news/novels	Yomitan zip	Filtering -> Frequency List File

Dictionaries are indexed once into ~/.anki_miner/dicts/ (drag to reorder the chain). The pitch and frequency pickers accept a raw CSV/TSV or a Yomitan zip, auto-converted to ~/.anki_miner/pitch_accent.csv / frequency.csv on Save. Bee's Character Dictionary builds a custom Yomitan dictionary from your AniList/VNDB media lists, so character names in the shows you mine resolve to real definitions; re-generate and re-import when your lists change.

Proper-noun filtering uses bundled name wordsets derived from JMnedict (JMdict/EDICT project, EDRDG, CC BY-SA 4.0).

Troubleshooting

Issue	Solution
"Cannot connect to Anki"	Start Anki and ensure AnkiConnect is installed.
"Deck not found"	The deck is created automatically when mining starts; if you meant a different deck, update the name in Settings.
"Note type not found"	Configure your note type's field names in Settings -> Anki.
"ffmpeg not found"	Install ffmpeg and add it to PATH.
No definitions found	Add a Yomitan dictionary in Settings -> Add Dictionary… (recommended), or enable the Jisho fallback (slower, rate-limited).
Audio is wrong language	The tool tries Japanese audio tracks first, then falls back to the default.
Subtitles out of sync	Use the subtitle offset control in the GUI (range ±300 seconds).
AV1 won't preview	In-app AV1 preview needs a hardware AV1 decoder (RTX-30+/Tiger-Lake+). Without one, the pane shows an "AV1 can't be decoded for preview" notice. Mining is unaffected - screenshots are extracted by FFmpeg, not the preview.

Roadmap

List of ideas for future versions of Anki Miner. Not in priority order. Feature requests take precedence.

• Suggest a feature - Open an issue.

• Discuss the roadmap - Discussions.

• Features:

  • UI language selection.
  • Local subtitle creation tab: Opt-in tab to locally generate subtitles.
  • Reading tab: Mine manga and books.
  • Media library: Expand Analytics tab to display local media library across all media forms.

• Improvements:

  • Improved user onboarding: automatic recommended resource fetching, easier setup.

• Researching/Under consideration:

  • Android port.
  • Jellyfin integration.
  • Jimaku integration.

• Long-term:

  • Beyond Japanese: Mining other languages.

Contributing

Contributions of any kind are welcome. If you want to support the project, please share it with others who may benefit from it.

• New here? Start with CONTRIBUTING.md.
• Architecture overview: ARCHITECTURE.md.
• Testing strategy: TESTING.md.
• Code of Conduct: CODE_OF_CONDUCT.md.
• Security: SECURITY.md.

Bug reports and feature requests -> Issues. General questions and discussion -> Discussions or Discord.

Special Thanks

Sincere thanks to people who made exceptional contributions to the project:

★ StyraxBenzoin - Brilliant feature suggestions, new release testing, community building

See CONTRIBUTORS.md for everyone who has made any kind of contribution to the project.

License

GNU General Public License v3.0. See LICENSE.