DavidVentura/offline-translator

Use Firefox Translation Models for on-device translation on Android

What it solves

This project provides a completely offline translation tool for Android, allowing users to translate text, images, and documents (PDF/ODT) without needing an internet connection or sending data to external servers.

How it works

The app uses on-device machine learning models for all its core functions. It utilizes Firefox's translation models for text, PaddleOCR for image text extraction, and cld2 for automatic language detection. Inference is handled by the slimt and MNN engines to ensure the models run efficiently on mobile hardware. It also includes a built-in dictionary based on Wiktionary data and supports various TTS (Text-to-Speech) engines like Piper and Kokoro.

Who it’s for

Android users who prioritize privacy, work in areas with limited connectivity, or need a translation tool that works entirely on-device.

Highlights

  • Complete Offline Capability: Download language packs once and translate forever without internet.
  • Multimodal Translation: Supports text, images, and PDF/ODT documents.
  • Broad Language Support: Supports a wide array of languages including Arabic, Chinese, Japanese, Korean, and many European languages.
  • Integrated Tools: Includes automatic language detection, transliteration for non-latin scripts, and a built-in word dictionary.
  • Developer API: Exposes an API that allows other Android apps to request translations.

Related

  • Project
    niedev/RTranslator

    An offline, real-time translation app for Android that uses on-device AI models like Whisper and NLLB to enable private, internet-free conversations.

  • Project
    ciddwd/overlay-translator

    Screen Translator is an Android app that captures the screen, runs OCR, translates the text (via on‑device models, LLM APIs, or traditional MT services), and overlays the result back onto the screen. It supports real‑time translation, batch image processing, word‑level dictionary lookup, TTS, and extensive customization, with both offline and cloud options.

  • Project
    tianclll/Ace-Translate

    A privacy-focused, offline document translation tool that translates various file formats while preserving original layouts using local LLMs and OCR.

  • Project
    dineshsoudagar/local-llms-on-android

    An Android application that enables fully offline, private LLM inference on-device and can act as a local LAN server for other devices via an OpenAI-compatible API.

  • Project
    egdels/makeacopy

    An offline Android document scanner with OCR that converts paper documents into searchable PDFs without using cloud services or tracking.