{"slug": "show-hn-sygal-convert-pdfs-scans-and-web-pages-to-markdown-locally", "title": "Show HN: Sygal – Convert PDFs, scans and web pages to Markdown, locally", "summary": "Sygal launched as a local document-conversion tool that turns PDFs, Word, Excel, PowerPoint, images, scans, web pages and YouTube links into clean Markdown and structured JSON on macOS 12+ and Windows 10+, priced at a €25 one-time purchase with a 14-day free trial and no subscription or account. The developer says converting visual and web content to text can run roughly 2 to 7x lighter on tokens, with exact figures varying by file, and offers OCR through OpenAI, Claude, Mistral, NVIDIA, Gemini or a custom provider using the user's own API key. Sygal supports 29 formats, batch conversion, a persistent searchable local library, and a token count shown on every document.", "body_md": "[NewLaunch offer: €25 one-time, no subscription](#pricing)\n\n# Turn any document into clean, AI-ready Markdown,\n\nright on your machine.\n\nPDF, Word, Excel, images, scans, web pages, even YouTube links: Sygal converts them locally into clean Markdown and structured JSON, ready to drop into a prompt, a knowledge base or a pipeline. On scans, images and web pages in particular, that also means far fewer tokens for your AI.\n\n14-day free trial · macOS 12+ · Windows 10+\n\nOne-time purchase · no subscription · no account\n\nReads everything you throw at it\n\n## From raw  to\n\nclean Markdown.\n\nDrop a dense PDF, a spreadsheet or a screenshot. Sygal returns clean Markdown you can read, or JSON your pipeline can parse.\n\n`⌘`\n\n`V`\n\n## A raw file and clean Markdown aren't the same to an AI.\n\nSygal normalizes every document into one clean, structured output your AI can actually work with. What that changes depends on where the file comes from.\n\n### 2 to 7x lighter, where it counts\n\nImages, scans, PDFs, web & YouTube\nA scan, a screenshot, a scanned PDF or a web page carries a lot your AI pays to read but never uses: pixels, layout, markup. Converted to text, the same content can run roughly 2 to 7x lighter on tokens, and the model reads what matters. YouTube links come in as clean transcripts, ready to summarize or search.\n\nThe gain is largest on visual and web content; exact figures vary with each file.\n\n### One clean, consistent output\n\nWord, Excel, PowerPoint\nAlready-structured files get a different win: Sygal standardizes them into the same clean Markdown and JSON as everything else. One predictable output for your whole pipeline, ready to parse, search and reuse, with no format-by-format handling.\n\nWhatever a document starts as, it ends the same way: clean, structured, and ready for your AI.\n\n## Drop. Convert. Review.\n\nExport.\n\nFrom a raw file to something usable, in seconds.\n\n### Drop\n\nA file, a URL, or a screenshot with Cmd+V. Sygal detects the format automatically.\n\n`⌘`\n\n`V` to paste\n\n### Convert\n\nFully local processing. For OCR on an image or scan, the provider of your choice, with your own key.\n\n### Review\n\nNative preview of the original file right next to the result. Edit the Markdown or JSON directly before exporting, nothing is locked.\n\n### Export\n\nMarkdown, JSON, or both at once. Export right away, and the result also stays in your local library, searchable anytime.\n\n## A full conversion engine,\n\n not just an exporter.\n\nThree groups of features: the essentials, what few tools offer, and what you need for daily use and volume.\n\n### The essentials\n\n29 supported formats (PDF, Word, Excel, PowerPoint, HTML, email, EPUB...)\n\nClean Markdown output and structured JSON\n\nNative preview of the original document, next to the result\n\nEdit the result before exporting\n\n### What few tools offer\n\n- OCR of your choice: OpenAI, Claude, Mistral, NVIDIA, Gemini or a custom provider, with your own API key\n- Direct import from a URL\n- A persistent local library, with full-text search\n- Token count shown on every document, so you see exactly what a model reads\n\n### For daily use and volume\n\n- Batch conversion\n- Filters and search in the library\n- Simple retry if a file fails\n- Direct copy-paste (Cmd+V) for screenshots\n\n## Three ways to use Sygal.\n\nThree profiles, one conversion engine.\n\n### Developers and AI builders\n\nPrepare your documents for a RAG pipeline, a vector store, or an agent, Markdown and JSON ready to use directly, with no extra cleanup step.\n\n### Professions handling sensitive documents\n\nLegal, accounting, HR, healthcare. Your contracts, payslips or case files never leave your machine, except the images you choose to send to OCR.\n\n### Everyday document use\n\nMeeting notes, internal documentation, research. A local, searchable library of everything you've converted.\n\n## Your OCR, your rules.\n\nImages run through the OCR provider you pick, with your own API key. Pick on cost and volume, and switch whenever you like.\n\nBilled per token, by image resolution.\n\nEveryday, mixed documents.\n\nFlat price per page, with an even cheaper async batch mode.\n\nLarge volumes of scans.\n\nBilled per token; the priciest at volume.\n\nWhen you specifically want Claude.\n\nNVIDIA NIM and Gemini are also available, along with a custom provider. NVIDIA offers a free option to get started with no API budget.\n\nOCR runs through your own API key and the engine you choose: no markup, swap anytime. Your documents are converted 100% locally and never leave your machine; only OCR on an image and importing a URL you choose reach the network.\n\n## Your documents stay on your machine.\n\nTwo columns, no ambiguity: what stays, what can leave.\n\n### Stays on your machine\n\n- Your files (Word, Excel, PDF, HTML, email...)\n- The text converted to Markdown and JSON\n- Your local library and its history\n- Your API keys, encrypted locally\n\n### Can go over the network, on your request\n\n- An image or a scan, sent to the OCR provider you choose, with your own key\n- A URL, if you import one\n\nNo account to create. No telemetry. Sygal never sees your documents.\n\n[See the full privacy policy](https://sygal.app/privacy)\n\n## Your AI agents deserve\n\nclean Markdown too.\n\nThe same conversion engine exists on the command line. One-command install, strict JSON output for your scripts, compatible with orchestrators like Hermes or OpenClaw.\n\n`npm install -g sygal-cli`\n[Explore Sygal CLI](https://sygal.app/cli)\n\n## What the people using it have to say.\n\nThree reviews, three different uses.\n\nPrivacy isn't negotiable in my line of work. Sygal converts my files locally, no cloud, no account. I can finally get AI-ready documents without compromising my clients' data.\n\nLaurence C.\n\nExecutive Assistant\n\nI feed Sygal's JSON output straight into my AI pipelines. The structure is consistent every time, exactly what I needed.\n\nThomas S.\n\nCEO\n\nFast and efficient. It saves half a day of processing, for me and for the teams. Easy to use and genuinely useful.\n\nJonathan D.\n\nSenior Director\n\n## One price. One purchase.\n\nNo subscription.\n\nNo usage meter, no surprise renewal.\n\nOne-time purchase, launch offer\n\n- Licence for 2 seats, usable on the desktop app or the CLI, your choice\n- All features: conversion, OCR (BYOK), library, batch export\n- Updates included for the major version\n- 14-day free trial before purchase\n- Refund available within 14 days\n\n[Start free trial](#download)\n\nNo card required for the trial. No subscription, ever.\n\nNeed several licences for your team? [See the team offer](https://sygal.app/pro)\n\n## Questions, answered.\n\nEverything you might want to know before you try Sygal.\n\nYes. Documents are converted locally with MarkItDown, so they never leave your machine and there's no account to create. Only images you send through OCR, and URLs you choose to import, reach the network. You choose from built-in providers (OpenAI, Claude, Mistral, NVIDIA NIM) or add any custom provider with your own API key.\n\n“I'm an independent developer in Paris. I built Sygal for two reasons: to stop using tools that upload everything, lock you into a subscription, and still hand back messy text; and to stop burning through my AI credits. A raw document drags along a lot of noise an AI has to read without needing it. Sygal is the tool I wanted for myself: local, paid once, built to hand my AIs clean text. If it spares you the same hassle, that's the whole point.”\n\nCyrill Semah\n\nCreator of Sygal\n\n## Stop copy-pasting.\n\nStart converting.\n\n14-day free trial. No card required. One-time purchase after that, no subscription.", "url": "https://wpnews.pro/news/show-hn-sygal-convert-pdfs-scans-and-web-pages-to-markdown-locally", "canonical_source": "https://sygal.app", "published_at": "2026-10-15 16:26:16+00:00", "updated_at": "2026-10-15 16:53:05.283234+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "ai-infrastructure"], "entities": ["Sygal", "OpenAI", "Claude", "Mistral", "NVIDIA", "Gemini", "macOS", "Windows"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-sygal-convert-pdfs-scans-and-web-pages-to-markdown-locally", "markdown": "https://wpnews.pro/news/show-hn-sygal-convert-pdfs-scans-and-web-pages-to-markdown-locally.md", "text": "https://wpnews.pro/news/show-hn-sygal-convert-pdfs-scans-and-web-pages-to-markdown-locally.txt", "jsonld": "https://wpnews.pro/news/show-hn-sygal-convert-pdfs-scans-and-web-pages-to-markdown-locally.jsonld"}}