AIAny
AI Client2024
Icon for item

BabelDOC

Translates scientific PDFs while keeping the original layout intact: parses text, tables, and figures, then re-renders bilingual or monolingual output via any OpenAI-compatible LLM. Tuned for English-to-Chinese papers, with CSV glossary support.

Introduction

Most tools that translate a PDF treat it as a bag of loose text, and the result is a mess: equations break, two-column flow collapses, and tables turn to soup. BabelDOC's bet is that translation and layout are two separate problems. It first parses a paper into a structured model — text blocks, figures, tables, formulas — translates only the language, then re-renders a new PDF that mirrors the original page geometry.

What Sets It Apart
  • Parse-then-render pipeline: layout fidelity comes from reconstructing the document, not patching strings in place, so a translated page still reads like the paper it came from.
  • Bring-your-own LLM: any OpenAI-compatible endpoint works, so you control cost, quality, and privacy rather than being locked to one provider.
  • Bilingual or monolingual output: side-by-side originals make it a study aid, not just a translator — useful when you don't fully trust the model on technical terms.
  • CSV glossaries: pin domain terminology across a whole document, which matters more in scientific text than raw fluency.
Who It's For

Great fit if you read English research papers and want a Chinese (or bilingual) copy that keeps figures, tables, and equations where they belong — especially paired with its Zotero and Immersive Translate integrations. Look elsewhere if you need non English-to-Chinese pairs (other directions are largely untested), heavily scanned or image-only PDFs, or pixel-perfect output: it skips very large pages and can misparse author and reference sections.

Information

  • Websitegithub.com
  • OrganizationsFunstory.ai
  • Authorsfunstory-ai
  • Published date2024/11/13

Categories

More Items

GitHub
AI Image2026

Node-based infinite-canvas web workstation for iterative visual creation — integrates image/video generation, reference editing, prompt library, multi-agent assistants, and asset management. Runs in-browser with configurable OpenAI-compatible endpoints; suited for local/personal deployment (AGPL-3.0).

GitHub
AI Client2026

Provides a deployable personal AI assistant that runs locally or in the cloud, supports multi-channel chat, extensible Skills/Plugins, and local-model runtimes. Key features include three-layer memory, kernel-level sandboxing and tool/file guards, and bundled QwenPaw-Flash local models for zero-API deployments.

GitHub

Provides a local-first web-intelligence layer for AI agents: search, fetch, crawl, extract, cache, find-similar and agent-style research without API keys or per-query billing, running as an MCP server, REST daemon, or SDK.