GitHub - Azure/co-op-translator: Easily automate the translation of your documentation into multiple languages, powered by Azure AI Services

Easily automate and maintain translations for your educational GitHub content across multiple languages as your project evolves.

Start here: Choose your workflow | Configuration | CLI | Python API | MCP Server

🌐 Multi-Language Support

Supported by Co-op Translator

Prefer to Clone Locally?

This repository includes 50+ language translations which significantly increases the download size. To clone without translations, use sparse checkout:

Bash / macOS / Linux:
git clone --filter=blob:none --sparse https://github.com/Azure/co-op-translator.git
cd co-op-translator
git sparse-checkout set --no-cone '/*' '!translations' '!translated_images'
CMD (Windows):
git clone --filter=blob:none --sparse https://github.com/Azure/co-op-translator.git
cd co-op-translator
git sparse-checkout set --no-cone "/*" "!translations" "!translated_images"
This gives you everything you need to complete the course with a much faster download.

Overview

Co-op Translator helps you localize your educational GitHub content into multiple languages effortlessly. When you update your Markdown files, images, or notebooks, translations stay automatically synchronized, ensuring your content remains accurate and up to date for learners worldwide.

Use it from the CLI for repository translation, from the Python API for automation, or through the MCP server for agent and editor workflows.

Example of how translated content is organized:

How translation state is managed

Co-op Translator manages translated content as versioned software artifacts,
not as static files.

The tool tracks the state of translated Markdown, images, and notebooks using language-scoped metadata.

This design allows Co-op Translator to:

Reliably detect outdated translations
Treat Markdown, images, and notebooks consistently
Scale safely across large, fast-moving, multi-language repositories

By modeling translations as managed artifacts, translation workflows align naturally with modern software dependency and artifact management practices.

→ How translation state is managed

Related deep dives

Fixing Broken Markdown in AI Translation: Hardening a Production Pipeline

Get Started

Co-op Translator can be used from the CLI, the Python API, or the MCP server. Start with the workflow guide if you are choosing between local translation, automation, CI, and agent/editor integration.

Minimal CLI example after configuration:

python -m venv .venv
# Windows
.venv\Scripts\activate
# macOS/Linux
source .venv/bin/activate

pip install co-op-translator
translate -l "ko" -md
co-op-review -l "ko"

For first runs on large repositories, use --dry-run before writing translated files. See the CLI Reference for content type flags, logs, review, and link migration.

Container quick run with Bash/Zsh:

docker run --rm -it --env-file .env -v "${PWD}:/work" ghcr.io/azure/co-op-translator:latest -l "ko" -md

Container quick run with PowerShell:

docker run --rm -it --env-file .env -v ${PWD}:/work ghcr.io/azure/co-op-translator:latest -l "ko" -md

Features

Automated translation for Markdown, notebooks, and images
Keeps translations in sync with source changes
Works locally (CLI) or in CI (GitHub Actions)
Exposes Markdown, notebook, image, review, and project translation tools through MCP
Uses Azure OpenAI or OpenAI for provider-backed translation
Lets MCP host agents translate Markdown and notebook chunks without Co-op Translator LLM credentials
Uses Azure AI Vision for image text extraction and translation
Reviews translation structure and freshness with deterministic checks
Preserves Markdown formatting and structure

Docs

Microsoft-specific guide

Note

For maintainers of the Microsoft “For Beginners” repositories only.

Updating the “other courses” list (for MS Beginners repositories only)

Support us and foster global learning

Join us in revolutionizing how educational content is shared globally! Give Co-op Translator a ⭐ on GitHub and support our mission to break down language barriers in learning and technology. Your interest and contributions make a significant impact! Code contributions and feature suggestions are always welcome.

Explore Microsoft educational content in your language

Video presentations

👉 Click the image below to watch on YouTube.

Open at Microsoft: A brief 18-minute introduction and quick guide on how to use Co-op Translator.

Contributing

This project welcomes contributions and suggestions. Interested in contributing to Azure Co-op Translator? Please see our CONTRIBUTING.md for guidelines on how you can help make Co-op Translator more accessible.

Contributors

Code of Conduct

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Responsible AI

Microsoft is committed to helping our customers use our AI products responsibly, sharing our learnings, and building trust-based partnerships through tools like Transparency Notes and Impact Assessments. Many of these resources can be found at https://aka.ms/RAI. Microsoft's approach to responsible AI is grounded in our AI principles of fairness, reliability and safety, privacy and security, inclusiveness, transparency, and accountability.

Large-scale natural language, image, and speech models - like the ones used in this sample - can potentially behave in ways that are unfair, unreliable, or offensive, in turn causing harms. Please consult the Azure OpenAI service Transparency note to be informed about risks and limitations.

The recommended approach to mitigating these risks is to include a safety system in your architecture that can detect and prevent harmful behavior. Azure AI Content Safety provides an independent layer of protection, able to detect harmful user-generated and AI-generated content in applications and services. Azure AI Content Safety includes text and image APIs that allow you to detect material that is harmful. We also have an interactive Content Safety Studio that allows you to view, explore and try out sample code for detecting harmful content across different modalities. The following quickstart documentation guides you through making requests to the service.

Another aspect to take into account is the overall application performance. With multi-modal and multi-models applications, we consider performance to mean that the system performs as you and your users expect, including not generating harmful outputs. It's important to assess the performance of your overall application using generation quality and risk and safety metrics.

You can evaluate your AI application in your development environment using the prompt flow SDK. Given either a test dataset or a target, your generative AI application generations are quantitatively measured with built-in evaluators or custom evaluators of your choice. To get started with the prompt flow sdk to evaluate your system, you can follow the quickstart guide. Once you execute an evaluation run, you can visualize the results in Azure AI Studio.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.

Getting Help

If you get stuck or have any questions about building AI apps, join:

If you have product feedback or errors while building visit: