Home

TTSMate is a simple and efficient text-to-speech tool suitable for learning, reading assistance, and content creation scenarios.
It supports multiple languages and voice selections, enabling quick conversion of text into natural-sounding audio files. It is a practical tool for improving TTS batch conversion efficiency.
1. Features Overview
Section titled “1. Features Overview”TTSMate helps you efficiently use cloud TTS services to convert large volumes of text into audio files quickly, avoiding repetitive and tedious manual operations.
Key Features:
- Batch conversion of ebooks and documents
- Custom pronunciation replacement dictionary
- Automatic two-person dialogue voice conversion and multi-person dialogue voice generation
- Currently supports Apple TTS Engine (local), Azure TTS Engine (cloud), Qwen3TTS (local), MOSSTTS (local), KokoroTTS (local), with future extensibility for more cloud TTS engines
- Audio file export
2. Who Is It For
Section titled “2. Who Is It For”TTSMate is ideal for you if any of the following applies:
- You frequently convert articles and ebook content into audio files for listening or sharing
- You need to batch-generate voice content for learning, reading aloud, or content creation
- You want to reduce repetitive copy-paste operations for segmenting text
TTSMate will significantly improve your text-to-speech workflow efficiency.
3. Product Introduction
Section titled “3. Product Introduction”- Main Interface
- Batch Ebook Conversion
Simply organize your text structure using a Word editing tool—e.g., Heading 1 for chapter titles, body text for chapter content. The app will automatically identify chapters and batch-generate corresponding audio files.
Document format: .docx
- Pronunciation Dictionary (Pro User Feature)
Supports custom corrections for polyphonic characters and error-prone pronunciations, ensuring voice output better matches usage scenarios.
- Two-Person Dialogue Split (Pro User Feature)
Splits text by dialogue form using preset rules and automatically assigns A/B voices for audio generation, suitable for dialogue reading scenarios.
- Multi-Person Dialogue Generation (Pro User Feature)
By manually specifying speaker voices, supports multi-person dialogue audio generation.
Currently supports Apple TTS Engine (local), Azure TTS Engine (cloud), Qwen3TTS (local), MOSSTTS (local), KokoroTTS (local), with future extensibility for more TTS engines.
4. Privacy Policy
Section titled “4. Privacy Policy”TTSMate places great importance on user privacy protection and strictly complies with relevant laws and regulations.
- Information Collection
This app does not collect, store, or upload any personally identifiable information. The app does not require user registration or login.
- Text Data Processing
During speech synthesis, user-entered text content is sent to Microsoft Azure Speech Services via the network solely for generating speech results. This app does not save, analyze, or use it for any other purposes.
- Information Storage
Audio files generated by this app are stored only on the user’s local device. Third-party TTS engine credentials are securely stored using Apple’s keychain tool with encryption.
- Information Disclosure
This app does not disclose any user personal information or text content to any third party.
- Privacy Policy Updates
Any updates to this privacy policy will be communicated within the app. Continued use of the app after updates constitutes acceptance of the latest privacy policy.
5. Contact
Section titled “5. Contact”Contact the author: yangxuehui@outlook.com