# Read PDF Aloud — Full Reference > [Read PDF Aloud](https://readpdfaloud.com/) is a browser-based text-to-speech tool that reads documents aloud using natural AI voices. Despite the name, it supports far more than PDF — upload ebooks, Office documents, plain text, Markdown, and more. All file parsing happens locally in the browser; your documents never leave your device. ## Key facts - **Multi-format support**: PDF, EPUB, MOBI, AZW3/KF8, DOCX, PPTX, ODT, ODP, RTF, TXT, and Markdown. - **400+ voices across 140+ languages**: Including regional variants and accents. - **Free to use**: New users receive 100 credits on registration. All users get 5 free credits per day (do not carry over). - **No installation required**: Runs entirely in the browser. Fully cross-platform — PC, Mac, Android, iOS, and Linux. - **Privacy-first**: File parsing is local. Only the text sent to the TTS API leaves your device, and only when you hit Play. --- ## Pages and tools ### Main pages - [Home](https://readpdfaloud.com/) — Landing page. Upload a document to get started. Includes how-to, features overview, FAQ, and recent blog posts. - [Voices](https://readpdfaloud.com/voices) — Browse and preview all 400+ AI voices. Filter by language and gender. Save favorite voices to your profile. - [Pricing](https://readpdfaloud.com/pay) — Credit purchase page. Three tiers available (see Credits section below). Includes FAQ and explanation of how credits are consumed. - [User Profile](https://readpdfaloud.com/user) — Shows paid credit balance, daily free credit balance, next daily refresh time, and full transaction history. - [Guide](https://readpdfaloud.com/guide) — Step-by-step guide to using Read PDF Aloud. - [Blog](https://readpdfaloud.com/blog) — Tips, guides, and updates. ### Reader - [Document reader](https://readpdfaloud.com/reader) — Drop zone for uploading files. Shows recently uploaded documents (stored locally). Entry point to the full reader. - [PDF / document reader](https://readpdfaloud.com/reader/pdf) — Full audio reader. Displays document text sentence by sentence. Click any sentence to jump playback to it. Includes page navigation, voice selector, speed control, copy text, and MP3 export. - [Text to speech reader](https://readpdfaloud.com/reader/text) — Same reader interface but for pasted or typed text instead of a file upload. ### Tools Each tool page is a dedicated landing page with SEO content (how-to steps, features, FAQ) plus an uploader that leads into the main reader. - [PDF to Speech](https://readpdfaloud.com/tools/pdf-to-speech) - [EPUB to Speech](https://readpdfaloud.com/tools/epub-to-speech) - [MOBI to Speech](https://readpdfaloud.com/tools/mobi-to-speech) - [AZW3 to Speech](https://readpdfaloud.com/tools/azw3-to-speech) - [KF8 to Speech](https://readpdfaloud.com/tools/kf8-to-speech) — KF8 is an alias for AZW3 (Amazon Kindle Format 8); both are handled identically. - [DOCX / ODT / RTF to Speech](https://readpdfaloud.com/tools/docx-to-speech) - [PPTX / ODP to Speech](https://readpdfaloud.com/tools/pptx-to-speech) - [Text to Speech](https://readpdfaloud.com/tools/text-to-speech) - [PDF to Text](https://readpdfaloud.com/tools/pdf-to-text) — Standalone batch OCR tool. Upload up to 10 PDF files (max 50 MB and 1,000 pages each). Extracts text from scanned PDFs using AI OCR. Output can be copied or downloaded. No audio playback — pure text extraction. --- ## Supported file formats All file parsing happens locally in the browser. For a full breakdown, see [Supported File Formats](https://readpdfaloud.com/blog/supported-file-formats-in-read-pdf-aloud). | Format | Extension(s) | Notes | |---|---|---| | PDF | `.pdf` | Text extracted page by page. Scanned PDFs auto-detected and offered OCR. | | EPUB | `.epub` | Parsed chapter by chapter. | | MOBI | `.mobi` | Amazon Kindle legacy format. | | AZW3 / KF8 | `.azw3`, `.kf8` | Amazon Kindle Format 8. Both extensions are identical. | | Word | `.docx` | Microsoft Word. | | PowerPoint | `.pptx` | Microsoft PowerPoint. | | OpenDocument Text | `.odt` | LibreOffice / OpenOffice. | | OpenDocument Presentation | `.odp` | LibreOffice / OpenOffice. | | Rich Text Format | `.rtf` | | | Plain Text | `.txt` | | | Markdown | `.md` | Markdown syntax stripped; plain text used for playback. | Additionally, text can be pasted directly into the [Text to Speech reader](https://readpdfaloud.com/reader/text) without any file upload. ### Scanned PDF detection and OCR Read PDF Aloud automatically measures a PDF's text density (average characters per page). If it falls below 50 characters per page, the document is flagged as a scanned (image-based) PDF. The user is then prompted with the estimated OCR cost before any processing begins. OCR is powered by Mistral AI and costs **2 credits per page**. Limits: 50 MB and 1,000 pages per file. --- ## Supported languages and voices 400+ voices across 140+ languages and regional variants. For the full list, see [Supported Languages](https://readpdfaloud.com/blog/supported-languages-in-read-pdf-aloud). Highlighted languages with regional variants: - **English** — US, UK, Australia, Canada, India, Ireland, New Zealand, Nigeria, Philippines, Singapore, South Africa, and more - **Mandarin Chinese** — Mainland China, Taiwan (Traditional), Hong Kong (Traditional), Liaoning dialect, Shaanxi dialect - **Spanish** — Spain, Mexico, US, Argentina, Colombia, Chile, and 16+ other regions - **Arabic** — Saudi Arabia, UAE, Egypt, Morocco, Algeria, and 11+ other regions - **French** — France, Canada, Belgium, Switzerland - **German** — Germany, Austria, Switzerland - **Portuguese** — Portugal, Brazil - **Hindi, Bengali, Tamil, Telugu, Kannada, Urdu** — India and regional variants - **Japanese, Korean, Thai, Vietnamese, Indonesian, Malay, Filipino** - **Russian, Ukrainian, Polish, Czech, Slovak, Romanian** - **And many more** — Afrikaans, Albanian, Amharic, Azerbaijani, Bosnian, Bulgarian, Catalan, Croatian, Danish, Dutch (NL/BE), Estonian, Finnish, Georgian, Greek, Gujarati, Hebrew, Hungarian, Icelandic, Irish, Javanese, Kazakh, Khmer, Lao, Latvian, Lithuanian, Macedonian, Maltese, Marathi, Mongolian, Burmese, Nepali, Norwegian Bokmål, Pashto, Persian, Sinhala, Slovenian, Somali, Sundanese, Swahili, Swedish, Turkish, Uzbek, Welsh, Zulu, and more Two voice tiers are available: - **Standard voices** — Powered by Microsoft Edge TTS. Lower credit cost. - **Premium voices** — Powered by Inworld AI. Higher quality prosody and naturalness. Higher credit cost. Voices can be previewed on the [Voices page](https://readpdfaloud.com/voices) and favorited to appear at the top of the voice picker in the reader. --- ## Credits system Credits are the in-app currency used to pay for TTS and OCR. Free credits are deducted before paid credits. ### Free credits | Type | Amount | Expiry | |---|---|---| | New user signup bonus | 100 credits | Never expire | | Daily free credits | 5 credits/day | Expire at end of day — do not carry over | ### Paid credit tiers | Plan | Price | Credits | |---|---|---| | Starter | $5.90 | 500 credits | | Most Popular | $19.90 | 4,000 credits | | Best Value | $99.00 | 40,000 credits | Paid credits never expire. Credits are charged per character for TTS (rate varies by voice tier) and per page for OCR (2 credits/page). The system checks your balance before starting any operation — no surprise charges. A **14-day refund policy** applies if purchased credits are entirely unused. Payments are processed by [Polar](https://polar.sh). --- ## How it works ### Text-to-speech flow 1. Upload a file (or paste text). 2. File is parsed locally in the browser — text is extracted and split into individual sentences. 3. A SHA-256 hash of the file's metadata and size is computed and used as a unique file ID. 4. Extracted text and metadata are saved to IndexedDB in your browser for instant re-access. 5. When you hit Play, each sentence's text is sent to the `/api/text-to-speech` endpoint. 6. The server routes the request to the appropriate TTS backend (standard or premium), deducts credits, and returns an MP3 audio blob. 7. The audio blob is cached in IndexedDB alongside the sentence — replaying a sentence you've already heard costs no additional credits. ### Local-first architecture All file parsing and text storage happen entirely in your browser. The only data that leaves your device is the sentence text sent to the TTS API when you play audio. This means: - Files are never uploaded to any server (unless you trigger OCR on a scanned PDF). - Your reading history, bookmarks, and cached audio all live in your browser's IndexedDB. - Previously heard sentences replay instantly from cache. --- ## Audio export Any sentence or section can be exported as an MP3 file directly from the reader. This lets you: - Listen offline on any device. - Create personal audiobooks from your documents. - Save study material for commutes. See [How to Export Audio from Read PDF Aloud](https://readpdfaloud.com/blog/how-to-export-audio-from-read-pdf-aloud) for step-by-step instructions. --- ## Use cases - **Audiobook creation** — Turn EPUB, MOBI, AZW3/KF8 or PDF novels into listening experiences. - **PDF to podcast** — Convert research papers and reports into audio you can listen to anywhere. - **Language learning** — Listen to texts in your target language with native-style voices to improve listening and pronunciation. - **Accessibility** — Auditory reading reduces eye strain and helps users with ADHD, dyslexia, or visual impairments stay focused. - **Multitasking** — Listen to documents while commuting, exercising, or doing other tasks. --- ## Blog - [How to Use Read PDF Aloud](https://readpdfaloud.com/blog/how-to-use-read-pdf-aloud) — Comprehensive usage guide. - [How to Make Your PDF Read Aloud](https://readpdfaloud.com/blog/how-to-make-your-pdf-read-aloud) — Survey of methods to read PDFs aloud across devices and platforms. - [How to Export Audio from Read PDF Aloud](https://readpdfaloud.com/blog/how-to-export-audio-from-read-pdf-aloud) — Step-by-step MP3 export guide. - [Supported File Formats in Read PDF Aloud](https://readpdfaloud.com/blog/supported-file-formats-in-read-pdf-aloud) — All supported formats with details on how each is processed. - [Supported Languages in Read PDF Aloud](https://readpdfaloud.com/blog/supported-languages-in-read-pdf-aloud) — Full language and regional voice variant list. - [What's New in January](https://readpdfaloud.com/blog/whats-new-in-january) — Release notes for user accounts, premium voices, and more. --- ## Authentication Sign in with Google. An account is required to use credits (both free daily credits and purchased credits). Guest users can upload files and view extracted text but cannot generate audio. --- ## Legal - [Terms of Service](https://readpdfaloud.com/terms-of-service) - [Privacy Policy](https://readpdfaloud.com/privacy-policy) - [Refund Policy](https://readpdfaloud.com/refund-policy) --- ## About the creator Read PDF Aloud is built by [Dkphhh](https://www.dkphhh.me), a solo indie developer. Other tools by the same creator: - [Video to Text](https://video2text.net/) - [Send to Feishu](https://dkphhh.me/tools/send-to-feishu/) - [Glitch Text Generator](https://cooltext.app/)