Last Updated: June 2026

1. Introduction Welcome to DocuVoice ("we," "our," or "us"). We are committed to protecting your privacy. This Privacy Policy explains how we collect, use, and safeguard your information when you use our mobile application, specifically designed for AI-powered PDF reading and offline Text-to-Speech (TTS) voice synthesis.

2. Document and Text Data (Core Functionality) To provide our core service (converting PDF documents into high-quality spoken audio with interactive sentence highlighting), we process document data. We have designed our system to prioritize your privacy and absolute data security:

• Local Layout-Aware Parsing: The extraction of plain text from your imported PDF files, paragraph restructuring, and sentence tokenization are performed entirely locally on your device. We do not use any external cloud servers to parse your documents.
• On-Device Neural Voice Synthesis (Zero-Cloud Transmission): Our voice synthesis engine runs locally using an embedded ONNX runtime environment. The plain text extracted from your PDFs is synthesized into speech waveforms on-device. Your document text, synthesized audio, and reading history are never transmitted to cloud servers or third-party AI providers.
• Local Storage (On-Device): All document metadata (e.g., document title, date added), raw binary PDF data, and reading progress (e.g., last read page index and sentence index) are stored exclusively on your device inside a local Core Data container. If you delete the DocuVoice app from your device, all your imported documents, settings, and reading history will be permanently lost.

3. Data Sharing and Third Parties We do not sell, rent, trade, or share your personal data, document text, or reading history. Because all document processing, text parsing, and audio generation are completed on-device without external APIs, no third-party cloud services have access to the documents you load into DocuVoice.

4. Security Because we follow a strict "on-device only" processing policy and store your documents and reading metrics entirely locally, the risk of data breaches involving your personal files or reading history is virtually non-existent. We do not maintain any databases or servers that house your personal documents.

5. Copyright and Content Disclaimer DocuVoice is designed to assist users in reading and listening to their own documents. Users are solely responsible for ensuring they have the legal right, ownership, or appropriate licensing to import, parse, and listen to the PDF files they load into the application. DocuVoice does not index, host, search, or distribute user-loaded documents.

6. Changes to This Policy We may update this privacy policy from time to time to reflect changes in our practices or for other operational, legal, or regulatory reasons. We will notify you of any changes by updating the "Last Updated" date at the top of this policy.

7. Contact Us If you have any questions or concerns regarding this Privacy Policy or how we handle your data, please contact us through the feedback or support section within the app settings.