Awesome GitHub RepositoriesTranslation Tools

GitHub Chinese is a browser-based utility designed to improve platform accessibility by translating interface elements, repository descriptions, and dynamic content into Chinese. It functions as a browser extension that modifies web content to assist non-native speakers with navigation and discovery. The tool employs a pattern-matching engine and mutation observers to identify and replace text strings as they appear on the page. It manages these translations through a local dictionary and configurable rule sets, which allow users to define exclusion criteria to protect specific elements like

Pyvideotrans is an automated video localization platform designed to transcribe, translate, and dub media content for international distribution. It functions as an end-to-end workflow that combines speech recognition, text translation, and synthetic voice generation to process video files into localized versions. The system distinguishes itself by offering a choice between local model inference for privacy and integration with third-party cloud services via user-provided credentials. This architecture allows users to maintain control over their billing and data security while utilizing modul

Immersive Translate is a browser-based translation tool that integrates third-party translation engines and large language models to provide automated, real-time text conversion directly within the web interface. It functions as a browser extension that intercepts and modifies web content, injecting translated text nodes into the document object model to maintain original page layouts and styling. The project distinguishes itself through its granular control over the translation process, allowing users to define site-specific rules, manage custom terminology glossaries, and customize translat

CopyTranslator is a clipboard-based translation tool and multi-engine translation client that monitors the system clipboard to provide automatic language conversion. It functions as an assistant that integrates large language models, cloud translation APIs, and digital dictionaries to produce context-aware translations and side-by-side reading views. The application includes a specialized PDF text cleaner to remove formatting artifacts and line breaks from copied content. It also features an optical character recognition extractor to convert images or screen captures into editable text for im

This application is a cross-platform desktop utility designed for automated translation, optical character recognition, and speech synthesis. It functions as a modular client that integrates various local and remote language services, allowing users to process text through hotkeys, clipboard monitoring, or direct input. The software distinguishes itself through a plugin-based architecture and a built-in automation framework. By exposing a local network interface, it enables external applications and scripts to programmatically trigger its translation and recognition workflows. Users can furth

Saladict is a browser extension designed to provide instant word definitions and translations by aggregating multiple online dictionary sources. It functions as a multilingual translation tool that retrieves and displays comprehensive word meanings within a unified interface, allowing users to access information without navigating away from their current webpage. The extension features a contextual lookup manager that organizes dictionary sources into profiles. These profiles automatically adjust the active translation sources based on the language or length of the selected text, ensuring tha

Ragas is an evaluation framework designed to measure the performance of retrieval-augmented generation pipelines and autonomous agent workflows. It provides a comprehensive suite of tools for benchmarking system outputs, utilizing language models as automated judges to score performance against defined rubrics and reference data. By standardizing inputs, retrieved contexts, and generated responses into a unified schema, the project enables consistent analysis across complex AI applications. The framework distinguishes itself through its ability to generate synthetic test datasets from existin

Paper2gui is a multi-modal AI toolkit and model GUI wrapper designed to deploy and run various artificial intelligence models through a visual interface. Its primary purpose is to provide a way to execute complex AI research papers and models without requiring manual software installation or coding. The project distinguishes itself by using a wrapper-based model interface that abstracts command line arguments into visual input fields, utilizing template-driven UI generation to create parameter sliders and forms based on the specific requirements of the underlying model. It includes a centrali

RTranslator is a speech translation application and background speech processor designed for real-time voice and text translation. It functions as a dual-language audio translator that detects different spoken languages to provide immediate voice translations for face-to-face interactions. The system includes a multi-device translation setup that synchronizes multiple devices over a network to facilitate group conversations through shared speakers. It also provides the ability to maintain audio processing and speech translation tasks while the device is on standby. The project covers a range

This project is an AI-powered bilingual book generator that translates EPUB, TXT, and SRT files into side-by-side bilingual editions while preserving the original formatting and structure. It functions as a translation workflow manager, orchestrating the process from file input to bilingual output with support for customizable prompts and resumable pipelines. The tool distinguishes itself through its multi-model AI backend abstraction, allowing users to select from various AI models to balance translation cost and quality for book content. It includes a resumable translation pipeline that sav

kiss-translator is a browser extension that provides an AI translation pipeline to render bilingual web content. It functions as a bilingual web translator, displaying original and translated text side-by-side while preserving the layout, formatting, and links of the original webpage. The tool distinguishes itself through deep AI customization, using terminology glossaries, conversation memory, and variable-based prompt templating to improve translation accuracy. It supports real-time translation streaming and allows users to compare outputs from multiple translation services simultaneously w

Read Frog is an AI-powered immersive translation browser extension that functions as a bilingual reading assistant and text explanation tool. It connects to over 20 AI providers, including OpenAI and Anthropic, with configurable endpoints, API keys, and model settings, enabling translation and explanation of web content directly in the browser. The extension distinguishes itself through several integrated capabilities. It translates webpage content by placing translations directly next to the original text for side-by-side comparison, and can process content from PDFs, videos, and comics. It

youtube-transcript-api is a Python library designed to retrieve and download subtitles and captions from YouTube videos using video IDs. It functions as an API client that extracts text and timing data for video content. The project includes a wrapper for automated translation, allowing transcripts to be converted into different target languages. It also features a retrieval system that supports routing requests through HTTP, HTTPS, or SOCKS proxies to avoid IP blocking and regional restrictions. The library provides tools for identifying available subtitle tracks and converting raw transcri

Heti is a CSS-based typographic enhancement library for Chinese web content. It applies standard Chinese typesetting rules entirely through stylesheets, without any JavaScript dependencies, handling punctuation compression, character alignment, mixed-script spacing, and baseline grid alignment for both simplified and traditional Chinese characters. The library distinguishes itself by supporting traditional vertical text layout flowing from top to bottom and right to left, alongside horizontal reading directions, using CSS Grid and writing-mode properties. It provides automatic dark mode adapt

OpenPromptStudio is an integrated toolset for constructing, translating, and managing prompt libraries to optimize outputs from generative AI and large language models. It functions as a prompt builder and visual editor designed to organize keywords and instructions for AI-generated content. The project features a visual-block construction interface that allows for the spatial arrangement of discrete keyword components. It includes a translation utility that converts prompts from Chinese to English to ensure compatibility with English-language models. The system provides prompt management th

Voice-over-translation is a userscript that adds real-time audio dubbing to videos on a wide range of websites, translating spoken content into Russian, English, or Kazakh from supported source languages. It works automatically as soon as a video page loads, extracting the original audio and replacing it with a translated voice-over without requiring manual intervention. The tool supports dozens of major streaming and social media platforms, including educational sites like Coursera and Udemy, file hosting services like Google Drive, live streaming platforms like Twitch, and adult content sit

Translation Agent is a Python-based system that uses a large language model to translate text through a multi-step agentic workflow. Rather than producing a single output, it generates an initial translation, then prompts the same LLM to critique its own work and produce improvement suggestions, and finally refines the translation based on that self-critique. This reflection-driven iterative refinement loop is the core mechanism for improving translation quality without requiring human feedback or additional training data. The system distinguishes itself through two key capabilities. First, i

This project is an LLM translation plugin and extension for the Bob translation tool. It connects the application to external large language models via API to provide real-time text translation, automated grammar correction, and content polishing. The plugin functions as an AI prompt engineering tool, allowing for the definition of custom system instructions and templates to control the style, tone, and reasoning depth of the output. It operates as a streamed API client that processes incremental text responses to display translation results in real time. Its capabilities cover translation b

SakuraLLM is a multi-format document translation system that hosts large language models for translating Japanese text into other languages. It functions as an inference server that exposes translation models through an OpenAI-compatible API, allowing any tool supporting the OpenAI client format to send translation requests. The system is designed as a glossary-aware translation engine that applies user-defined term dictionaries to ensure consistent translation of proper nouns and names across outputs. The project distinguishes itself by supporting multiple high-performance inference backends

crx-selection-translate is a multimodal translation browser extension designed to process text, images, PDFs, and audio-visual content. It provides a translation interface that operates across various digital formats, including a bilingual mode for web pages that displays translated content alongside the original text. The tool features a multi-engine comparison system that aggregates results from several translation services for selected text. It also includes an optical character recognition utility to extract and translate text from screenshots, clipboards, and image files. Additional cap