Yodesla

Extract text, sections and metadata from Word (DOCX), PowerPoint (PPTX), OpenDocument (ODT/ODP) and EPUB files by URL, up to 50 per run. $0.003 per document, no start fee; failed or unsupported files are never charged.

No public Store description is available yet.

No public Store description is available yet.

Turn images and scanned PDFs into text by URL, up to 50 files per run, with per-page confidence scores. Tesseract OCR, 6 languages. $0.005 per OCR'd page, no start fee. Weak on handwriting. Failed, unsupported or empty results are reported but never charged.

Extract per-page text and metadata from text-based PDFs by URL, up to 50 per run. $0.003 per successfully extracted PDF, no start fee. Scanned, encrypted, failed or corrupt files are reported but never charged. Built for RAG, indexing and search pipelines.

Read up to 200 RSS, Atom or JSON Feed URLs per run into one clean, deduplicated item list, with a publishedAfter filter for scheduled new-items-only runs. $0.002 per successfully parsed feed, no start fee. Failed or non-feed URLs are reported but never charged.

Check up to 500 trademark phrases per run against a snapshot of live US federal trademarks from official USPTO bulk data, with Nice-class filter and the snapshot date in every result. $0.002 per phrase checked, no start fee. Record lookup, not legal advice or clearance.

No public Store description is available yet.

Convert XLSX, CSV and TSV files from URLs into clean JSON — one dataset item per spreadsheet row — with all sheets included and types preserved. $0.01 per successfully converted file, no start fee. Failed, unsupported or corrupt files are reported but never charged.