BabelDOC

raw JSON →

0.5.24 verified Fri May 01 auth: no python

Yet Another Document Translator. Current version 0.5.24. Supports Python >=3.10 <3.14. Released roughly weekly.

pip install babeldoc[ocr]

Common errors

error ModuleNotFoundError: No module named 'babeldoc' ↓

cause The package is not installed or installed in a different environment.

fix

Run 'pip install babeldoc' in the correct Python environment.

error ImportError: cannot import name 'DocumentTranslator' from 'babeldoc' ↓

cause Old version of babeldoc or incorrect import path. The class was renamed in v0.5.

fix

Upgrade to latest: 'pip install --upgrade babeldoc'. Use 'from babeldoc import DocumentTranslator'.

Warnings

breaking Python 3.13 is not supported; requires Python >=3.10 <3.14. ↓

fix Use Python 3.10, 3.11, or 3.12.

gotcha The 'ocr' extra is required for OCR-based translation; otherwise, text extraction only. ↓

fix Install with 'pip install babeldoc[ocr]' and ensure you have Tesseract installed separately.

gotcha API key must be passed explicitly or set via environment variable; no default. ↓

fix Set OPENAI_API_KEY environment variable or pass api_key parameter.

Install

pip install babeldoc

Imports

DocumentTranslator
```
from babeldoc import DocumentTranslator
```
Main class for translating documents
TranslationConfig
```
from babeldoc import TranslationConfig
```
Configuration object for translation settings

Quickstart

Basic usage: instantiate DocumentTranslator with API key and model, then call translate with a TranslationConfig.

from babeldoc import DocumentTranslator, TranslationConfig

translator = DocumentTranslator(
    api_key=os.environ.get('OPENAI_API_KEY', ''),
    model='gpt-4o',
    source_lang='en',
    target_lang='zh'
)
config = TranslationConfig(
    input_file='input.pdf',
    output_file='output.pdf'
)
translator.translate(config)