Processed on your device

No server copy

No server upload

104 file formats

Free tools

Format ConvertlyFormat Convertly
EnglishEnglishEspañolSpanishPortuguêsPortugueseBahasa IndonesiaIndonesianFrançaisFrenchItalianoItalianРусскийRussianDeutschGermanPolskiPolishTiếng ViệtVietnameseไทยThaiTürkçeTurkishالعربيةArabic日本語Japanese한국어Korean中文Chinese繁體中文Chinese (Traditional)NederlandsDutchУкраїнськаUkrainianSvenskaSwedishDanskDanishעבריתHebrewहिन्दीHindiفارسیPersian
OCR Tools

OCR Tools

Private browser text extraction for images and scanned PDFs. Audio and video use Transcription, not OCR.

Choose a file or drag and drop

Drop an image or PDF here or

Choose file · Drag & drop · Public file link

  • Processed on your device
  • No conversion file stored on our servers
  • Maximum file size: 100 MB

Conversion runs in your browser. Files are not uploaded to Format Convertly servers.

Architecture: Image / PDF → Browser → Tesseract WASM → Text / Word / Excel / Searchable PDF. Audio / Video → Whisper WASM → TXT / SRT / VTT. Conversion files stay in this tab; models may download.

Flagship OCR & text tools

Image to TextFlagship OCR — photo to text, picture to text, extract text from image. Private Tesseract.js.Image to WordOCR any common image (JPG, PNG, WEBP, BMP, TIFF) into an editable DOCX.Image to ExcelOCR image tables into XLSX with heuristic row/column detection.Screenshot to TextPaste a screenshot with Ctrl+V and extract text in this tab — no save step.PDF OCRExtract text from PDFs — uses an existing text layer when present, otherwise OCRs scanned pages.OCR PDF to WordConvert scanned PDFs into editable DOCX with browser OCR.Searchable PDFAdd an invisible OCR text layer so you can Ctrl+F, select, and copy from scanned PDFs.Scanned Image to TextOCR for scans and document photos — recognize text locally with WebAssembly.OCROCR hub — free browser OCR for images with copy, TXT, and Word download.Speech to TextAudio/Video → Text/Subtitles — MP3, WAV, M4A, MP4, MOV, WEBM to TXT, SRT, or VTT in your browser.Video to TextMP4, MOV, WEBM, MKV, AVI → transcript (TXT) or subtitles (SRT/VTT). Video convert, not a video editor.Subtitle Time ShifterShift SRT/VTT cue times by seconds — fix late or early captions in your browser.

Format converters

Image OCR landings and Audio/Video → Text pairs under /converters — same private browser engines.

JPG to TextOCR JPEG photos to plain text.PNG to TextOCR PNG screenshots and scans.WEBP to TextOCR WEBP images to TXT.JPG to WordOCR JPG → editable DOCX.PNG to WordOCR PNG → editable DOCX.JPG to ExcelOCR JPG tables → XLSX.PNG to ExcelOCR PNG tables → XLSX.MP3 to TextSpeech → transcript / subtitles from MP3.WAV to TextSpeech → transcript / subtitles from WAV.M4A to TextSpeech → transcript / subtitles from M4A.MP4 to TextVideo speech → TXT / SRT / VTT.MOV to TextMOV audio → transcript or captions.WEBM to TextWEBM → text & subtitles on-device.MKV to TextMKV → transcript or SRT/VTT captions.AVI to TextAVI → TXT / SRT / VTT privately.

Why browser OCR matters

Classic online OCR uploads every scan to a remote queue. Format Convertly keeps recognition in a Tesseract.js WebAssembly worker so receipts, IDs, and product screenshots never need to leave the laptop — the same privacy model as our converters.

Which page should I open?

Start with Image to Text for the photo / picture / extract-text cluster. Use Image to Word or Image to Excel when the output format is the goal. Paste captures on Screenshot to Text. For PDFs, pick PDF OCR, OCR PDF to Word, or Searchable PDF.