Overview¶

Mirumoji is an open-source, self-hosted Japanese immersion toolkit. Drop in any video, anime episode, drama or audio clip and it gives you: clickable tokenized subtitles with dictionary pop-ups, Whisper-powered transcription, instant SRT/clip extraction, and one-click Anki deck export — all in Docker, all running on your own machine.

Optional Integrations

OpenAI Integration: Customizable GPT Breakdowns of Subtitles
Modal Integration: Install a CPU only version and run all GPU tasks on the cloud

Preview

View a Preview of the frontend (No backend running)

Documentation

Access full Documentantion

Features¶

Interactive Video PlayerClickable Japanese SubtitlesDictionaryText AnalyzerOpenAI IntegrationLocal Media ProcessingAudio TranscriptionProfile-Based Data Management

word_dialog — Subtitles are tokenized (`kuromoji.js`), allowing you to click individual words for information

dictionary — Dictionary (`kotobase`) page allowing wildcard searches.

text_analyzer — Copy and paste text for tokenized output with furigana and clickable words.

gpt_template — Modify System Message and User Prompt with `{sentence}` and `{word}` variables.

Video Conversion

Upload videos in various formats; they can be converted to MP4 for optimal playback.

SRT Generation

Generate subtitles for your videos. Runs FasterWhisper with modified parameters to increase accuracy for longer media such as Anime/ J-Drama episodes.

transcription — Transcribe Japanese audio from recordings or uploaded files.

Persistent Storage

Profile configurations and all other profile-related data is stored and managed via SQLite database by the backend.

Clip Saving

Setup¶

Docker Images

Both the frontend and backend have pre-built Docker images and are set up to work with Docker Compose.

Tip

The easiest setup is to run the GUI Launcher for your platform. For detailed instructions please refer to the Setup Guide

Image Sizes¶

Compressed Image Sizes