DeepL/deepl-python

Official Python library for the DeepL language translation API.

DeepL Python Library

What it is – An official Python client for the DeepL API, a commercial language‑AI service that provides high‑quality machine translation, text‑improvement (re‑phrasing), and document translation.

Key capabilities

  • Text translation – translate_text() accepts a single string or a list, auto‑detects the source language, and returns the translated text together with metadata (detected source, billed characters, model used). Options let you control sentence splitting, formality, glossaries, custom instructions, model type (quality‑ vs latency‑optimized), tag handling (HTML/XML), and more.
  • Write/Improve API – rephrase_text() can rewrite or improve a passage in the same language or change its variant (e.g., US vs. UK English). You can request a style (academic, business, casual, simple) or tone (confident, diplomatic, etc.).
  • Document translation – translate_document() / translate_document_from_filepath() handle full files (DOCX, PDF, etc.) by uploading, polling, and downloading the translated version. You can also call the lower‑level upload/status/download functions yourself.
  • Glossaries – Create, list, retrieve, and delete multilingual glossaries (user‑defined term mappings) via the new v3 endpoints. Glossaries can be supplied directly or uploaded from CSV.
  • Advanced features – Translation memory, style rules, custom instructions (up to 10 per request), and fine‑grained XML tag handling (splitting, ignoring, etc.).

Typical usage

import deepl
client = deepl.DeepLClient("YOUR_AUTH_KEY")
# Simple text translation
result = client.translate_text("Hello, world!", target_lang="FR")
print(result.text)   # → Bonjour, le monde !

# Re‑phrase English text in a business style
improved = client.rephrase_text(
    "A rainbouw has seven colours.",
    target_lang="EN-US",
    style=deepl.WritingStyle.BUSINESS.value,
)
print(improved.text)

Installation & requirements

  • Install with pip install --upgrade deepl (Python 3.9‑3.13 supported).
  • Depends on requests (≥ 2.32.4). On Ubuntu 22.04 you may need the python3‑cachecontrol package.

Who might use it – Developers building translation‑enabled apps, localization pipelines, content‑creation tools, or any service that needs to call DeepL’s translation or text‑improvement capabilities programmatically.

All information above is taken directly from the repository’s README.

Related

  • Project
    eggplants/deepl-cli

    A Python CLI (and library) that translates text via the DeepL web interface using Playwright, requiring no API key.

  • Project
    AnswerDotAI/fastcore

    A utility library that extends Python's core functionality with features inspired by Ruby and Haskell, providing enhanced data structures and functional programming tools.

  • Project
    OptimalScale/LMFlow

    LMFlow is an extensible Python toolbox for fine‑tuning large language models. It supports full‑parameter training, LoRA, the memory‑efficient LISA algorithm, QLoRA quantization, and a suite of speed‑up tricks (FlashAttention‑2, DeepSpeed, vLLM, SGLang). After training, it provides simple scripts for chat‑style inference and optional Gradio/Flask deployment. The library is designed for Linux/Colab environments and offers optional extras for multimodal models, distributed reward‑model inference, and more.

  • Project
    mistralai/client-python

    Official Python SDK for Mistral AI’s cloud APIs (chat, embeddings, audio, files, agents, etc.). Install via pip/uv/poetry, set `MISTRAL_API_KEY`, then call methods like `client.chat.complete(...)` synchronously or with `asyncio`. Includes Azure and GCP wrappers and support for streaming, pagination, retries, and more.

  • Project
    alexzhang13/rlm

    An inference engine and training environment for Recursive Language Models (RLMs) that enable LLMs to handle near-infinite context by programmatically decomposing tasks via recursive sub-calls in a REPL environment.