About this project
FunTTS is a modern Python text-to-speech (TTS) tool library designed to simplify the integration and switching of different TTS engines through a unified API interface. It supports multiple mainstream open-source and commercial engines, including Edge TTS, Azure TTS, Bark, Tortoise, eSpeak, and pyttsx3. Users can dynamically select engines via configuration files or code without modifying the core logic. The library has built-in support for three subtitle formats—SRT, VTT, and FRT—and can automatically generate and synchronize timelines. It also supports multi-speaker scenarios, facilitating the creation of conversational audio content. Additionally, FunTTS provides practical tools for audio merging, response merging, and batch processing, and supports asynchronous operations to enhance performance. The project structure is clear, containing base abstract classes, data models, engine implementations, and utility function modules, making it easy to extend with new engines. Installation is flexible, supporting the on-demand installation of specific engine dependencies as well as full installation options. The documentation is detailed, covering engine configurations, usage examples, troubleshooting, and development guides, making it suitable for various scenarios ranging from personal projects to enterprise-level applications.
Comments
0 Rating appears after 10 ratings
Sign in to join the discussion.