TTSMate

TTSMate - 在 macOS 上即时文本转语音

TTS Mate 帮助您将大量文本高效转换为语音文件，通过自动化处理流程，避免重复、繁琐的人工操作。 主要功能包括：支持电子书、文档内容的批量语音转换；支持自定义发音替换字典，修正多音字和易错发音； 支持双人对话语音模式，适用于对话类内容朗读；支持mac本地TTS引擎或第三方TTS引擎进行语音合成； 支持生成语音文件并导出保存到本地设备。

版本：1.1.1

开发者：学辉 杨

经常将文章、电子书内容转换为语音文件进行收听或分享的人士； 需要批量生成语音内容用于学习、朗读或内容创作的人士； 希望减少重复段落复制粘贴等机械操作的人士。

• 批量转换电子书：只需使用 Word 等编辑工具整理文本结构，例如将一级标题作为章节名称、正文作为章节内容，应用即可自动识别章节并批量生成对应的语音文件。
• 发音字典：支持对多音字、易错发音进行自定义修正，确保语音输出更符合日常使用习惯。
• 双人对话模式：通过预设对话规则，将文本按对话形式分割，并自动匹配 A / B 两种音色生成语音，适用于对话内容朗读场景。
• TTS 引擎支持：目前支持mac本地TTS引擎和AzureTTS引擎，并将根据用户反馈逐步增加更多引擎选择。
• 导出功能：支持生成语音文件并导出保存到本地设备。
• 隐私保护：严格保护用户隐私，不收集、存储或上传任何可用于识别用户身份的个人信息。

使用 Word 等编辑工具整理文本结构，例如将一级标题作为章节名称、正文作为章节内容， 应用即可自动识别章节并批量生成对应的语音文件。

在应用中，您可以对多音字、易错发音进行自定义修正，确保语音输出更符合日常使用习惯。

通过预设对话规则，将文本按对话形式分割，并自动匹配 A / B 两种音色生成语音， 适用于对话内容朗读场景。

TTSMate - Convert text to speech instantly on macOS

TTS Mate helps you efficiently convert large amounts of text into voice files through automated processing, avoiding repetitive and tedious manual operations. Main features include: supporting batch voice conversion of e-books and document content; supporting custom pronunciation replacement dictionary to correct polyphonic characters and error-prone pronunciations; supporting two-person dialogue voice mode, suitable for reading dialogue content; supporting mac local TTS engine or third-party TTS engine for voice synthesis; supporting generating voice files and exporting them to local devices.

Version: 1.1.1

Developer: 学辉 杨

People who often convert articles and e-book content into voice files for listening or sharing; People who need to batch generate voice content for learning, reading or content creation; People who want to reduce mechanical operations such as repeated paragraph copying and pasting.

• Batch Convert E-books: Just use editing tools like Word to organize text structure, such as using first-level headings as chapter names and body text as chapter content, and the app will automatically identify chapters and batch generate corresponding voice files.
• Pronunciation Dictionary: Support custom correction of polyphonic characters and error-prone pronunciations to ensure voice output better matches daily usage habits.
• Two-person Dialogue Mode: Through preset dialogue rules, split text into dialogue form and automatically match A/B two tones to generate voice, suitable for dialogue content reading scenarios.
• TTS Engine Support: Currently supports mac local TTS engine and AzureTTS engine, and will gradually add more engine options based on user feedback.
• Export Functionality: Support generating voice files and exporting them to local devices.
• Privacy Protection: Strictly protect user privacy, not collecting, storing or uploading any personal information that can be used to identify users.

Use editing tools like Word to organize text structure, such as using first-level headings as chapter names and body text as chapter content, and the app will automatically identify chapters and batch generate corresponding voice files.

In the app, you can make custom corrections for polyphonic characters and error-prone pronunciations to ensure that the voice output better matches daily usage habits.

Through preset dialogue rules, split text into dialogue form and automatically match A/B two tones to generate voice, suitable for dialogue content reading scenarios.