LibreTranslate — Self-Hosted Translation API with No Rate Limits
LibreTranslate is a self-hostable translation API powered by open-source Argos Translate models. No API keys, no rate limits, no data sent to third parties — a drop-in replacement for Google Translate when privacy matters.
Staging sûr pour cet actif
Cet actif est d'abord staged. Le prompt copié demande à l'agent d'inspecter les fichiers staged avant d'activer scripts, config MCP ou config globale.
npx -y tokrepo@latest install 3109a712-381e-11f1-9bc6-00163e2b0d79 --target codexStage les fichiers d'abord; l'activation exige la revue du README et du plan staged.
What it is
LibreTranslate is a self-hosted machine translation API powered by open-source Argos Translate models. It provides a REST API for text translation between supported languages with no API keys, no rate limits, and no data sent to third parties. LibreTranslate is a privacy-focused, drop-in replacement for Google Translate API.
LibreTranslate is for developers and organizations who need machine translation without sending text to cloud translation services, whether for privacy, compliance, or cost reasons.
The project is actively maintained with regular releases and a growing user community. Documentation covers common use cases, and the open-source nature means you can inspect the source code, contribute fixes, and adapt the tool to your specific requirements.
How it saves time or tokens
Google Translate API and DeepL charge per character with usage limits. LibreTranslate is free after the initial server setup. For applications that translate high volumes of text (documentation localization, chat translation, content migration), the cost savings are significant. Running locally also eliminates network latency for translation requests.
How to use
- Deploy LibreTranslate via Docker.
- The API is available on port 5000 by default.
- Send POST requests to
/translatewith source text, source language, and target language.
Example
# Deploy via Docker
docker run -d --name libretranslate -p 5000:5000 libretranslate/libretranslate
# First run downloads language models (may take several minutes)
# Translate text
curl -X POST http://localhost:5000/translate \
-H 'Content-Type: application/json' \
-d '{"q": "Hello world", "source": "en", "target": "es"}'
# Response: {"translatedText": "Hola mundo"}
# List supported languages
curl http://localhost:5000/languages
Related on TokRepo
- AI Tools for Content -- Content translation and localization tools
- AI Tools for Self-Hosted -- Self-hosted application tools
Common pitfalls
- Language model downloads happen on first startup and can be several gigabytes. The container may appear unresponsive during this phase. Check logs with
docker logs libretranslate. - Translation quality varies by language pair. Common pairs (English-Spanish, English-French) are good. Rare pairs may produce lower quality. Test your specific language pair before relying on it.
- LibreTranslate defaults to allowing all origins for CORS. For production, restrict origins and consider adding API key authentication with the
--api-keysflag.
Before adopting this tool, evaluate whether it fits your team's existing workflow. Read the official documentation thoroughly, and start with a small proof-of-concept rather than a full migration. Community forums, GitHub issues, and Stack Overflow are valuable resources when you encounter edge cases not covered in the documentation.
Questions fréquentes
LibreTranslate supports 30+ languages including English, Spanish, French, German, Chinese, Japanese, Korean, Arabic, Russian, Portuguese, and many more. The full list depends on the installed Argos Translate models.
Google Translate generally produces higher quality translations, especially for complex sentences. LibreTranslate runs locally with no data sharing and no per-character costs. Quality is acceptable for most practical use cases.
Yes. LibreTranslate uses Argos Translate models, which can be trained on custom parallel corpora. You can add domain-specific models for specialized vocabulary.
The API translates one text block per request. For batch translation, send multiple requests. The self-hosted deployment has no rate limits, so you can parallelize as much as your hardware supports.
LibreTranslate runs on CPU. A machine with 4GB RAM and 2 CPU cores handles typical workloads. GPU acceleration is not required but can speed up translation for high-volume deployments.
Sources citées (3)
- LibreTranslate GitHub— LibreTranslate is a self-hosted translation API
- Argos Translate— Powered by Argos Translate open-source models
- LibreTranslate Website— REST API for machine translation
En lien sur TokRepo
Fil de discussion
Actifs similaires
LibrePhotos — Self-Hosted AI-Powered Photo Management
A self-hosted open-source photo management service with automatic face recognition, object detection, and geolocation tagging powered by machine learning.
Gotify — Self-Hosted Push Notification Server
Gotify is a simple, self-hosted push notification server with a REST API, real-time WebSocket delivery, and a web UI plus Android app for receiving alerts.
Kimai — Self-Hosted Open Source Time Tracking
A professional time-tracking application for teams and freelancers with project management, invoicing, and detailed reporting, all self-hosted and privacy-respecting.
Vikunja — Self-Hosted Open Source To-Do and Project Management
Vikunja is an open-source task management application written in Go. It offers lists, kanban boards, Gantt charts, and CalDAV sync — a self-hosted alternative to Todoist, Trello, and Asana.