TeToS provides a unified Python interface for multiple cloud-based Text-to-Speech (TTS) services, simplifying the process of generating speech from text for developers and researchers. It abstracts away the complexities of individual provider APIs, offering a consistent way to integrate various TTS engines into applications.

How It Works

TeToS acts as a wrapper around popular TTS APIs, including OpenAI, Azure, Google, Baidu, and others. Each supported provider is implemented as a distinct module, handling authentication, request formatting, and response parsing specific to that service. This modular design allows for easy addition of new TTS providers and maintains a clean separation of concerns.

Quick Start & Requirements

• Primary install: pip install tetos
• Requirements: Python 3.8+
• Documentation: CLI Usage, API Usage

Highlighted Details

• Supports 9 TTS providers: Edge-TTS, OpenAI, Azure, Google, Volcengine, Baidu, Minimax, Xunfei, and Fish Audio.
• Offers both a Command Line Interface (CLI) and a Python API for integration.
• Respects standard proxy environment variables (HTTP_PROXY, HTTPS_PROXY, ALL_PROXY, NO_PROXY).
• Allows specifying language and voice options for supported providers.

Maintenance & Community

The project is maintained by frostming. Further community or roadmap information is not detailed in the README.

Licensing & Compatibility

• License: Apache License 2.0
• Compatibility: Permissive license suitable for commercial and closed-source applications.

Limitations & Caveats

SSML support is listed as a future enhancement (TODO). Specific provider requirements, such as API keys and service region configurations, must be met and configured by the user.