Audoc: Document to Audio

Audoc turns documents into listening scripts made for understanding, not just robotic text-to-speech. Import PDF, Word, PowerPoint, Excel, OpenDocument, EPUB, HTML, RTF, Markdown, text, CSV, or an image. Audoc preserves headings, paragraphs, tables, charts, diagrams, and illustration locations where the source format exposes them, then reads them with clear navigation and playback controls. Choose Narrated mode for section cues, table orientation, and explicit visual descriptions, or Plain Read for a closer reading of the extracted source. PRIVATE BY DEFAULT Document parsing, language detection, system speech, and saved results work on your device. Download Gemma 4 E2B or E4B for private AI translation and richer visual descriptions. Download Supertonic 3 for multilingual offline neural speech. Optional downloads are large and removable. TRANSLATE AND LISTEN Translate the complete listening script into Korean, English, Japanese, Chinese, Spanish, French, German, Portuguese, Hindi, or Arabic. Progress is saved part by part, can be paused, and resumes after interruption. Select a compatible voice for the translated language. DESIGNED FOR REAL LISTENING Playback supports screen lock, background audio, speed control, part navigation, and lock-screen controls. Retry one visual description or rebuild the complete script without reimporting the document. OPTIONAL CLOUD AI For non-confidential documents, you can enter your own Gemini or OpenAI API key. Cloud processing remains off until you explicitly enable it for a document. Provider charges and terms apply. Audoc requires iOS or iPadOS 18 or later. Imports are limited to 256 MB, with tighter safety limits for individual text, image, and archive components. AI quality, speed, memory use, and voice availability depend on your device, installed models, source document, and language. Legacy binary Office files may provide less structure than modern Office Open XML files.