PaperSpeak

PaperSpeak turns the documents you already have into a calm, focused listening experience. PaperSpeak is free to download and use, with no ads, subscriptions, or in-app purchases. Import a file or paste text, choose a voice, and listen while PaperSpeak highlights each sentence. Tap any sentence to jump directly to it, adjust the playback speed, and continue later from where you stopped. READ AND LISTEN TOGETHER • Follow clear sentence-by-sentence highlighting • Tap any sentence to start from that point • Adjust playback speed from 0.5× to 2× • Continue listening in the background • Resume each document from your saved position BRING YOUR OWN DOCUMENTS • Import PDF, TXT, RTF, HTML, DOCX, and Pages files • Read text-based and scanned PDFs with on-device recognition • Keep PDF reading order while common repeated headers, footers, and page numbers are removed • Follow PDF page progress and resume where you stopped • Import several documents at once • Paste text to create a document instantly • Share text, webpages, and supported document files directly from other apps • Webpage import focuses on the main article and skips common banners, navigation, sidebars, related-content grids, comments, and footers • Share one or several screenshots and extract editable text on-device • Older DOC files can be converted to DOCX before import KEEP YOUR LIBRARY ORGANIZED • Create and rename folders • Select several documents at once • Move documents between folders • Rename or delete documents whenever you like CHOOSE HOW PAPER SPEAKS • Use built-in Apple voices offline • Choose from 13 language options: Mandarin, Cantonese, US and UK English, Japanese, Korean, Spanish, French, German, Italian, Brazilian Portuguese, Hindi, and Arabic • Set a favorite voice for each selected language • Optionally connect Azure, OpenAI, or ElevenLabs with your own API key PaperSpeak does not require an account and does not contain advertising or tracking. Documents, screenshot recognition, and scanned-PDF recognition stay on your device when using built-in voices. When you choose a cloud speech engine, the text being spoken is sent directly to that provider to generate audio. Optional cloud providers may charge for their services; see each provider’s official website for more information.