This project provides a text-to-speech (TTS) service that leverages Microsoft Azure Speech Services for high-quality voice synthesis. It is designed for developers and users needing to integrate TTS capabilities into applications or use a standalone service, offering flexibility through multiple languages, voices, adjustable speech parameters, and various audio formats.

How It Works

The service acts as a wrapper around Microsoft Azure's TTS API, providing a user-friendly interface and compatibility with the OpenAI TTS API. It handles long text inputs by automatically segmenting and merging them, ensuring smooth audio generation. The architecture supports customization via environment variables or YAML configuration files for parameters like port, Azure region, default voice, speech rate, pitch, and audio format.

Quick Start & Requirements

• Docker Deployment: docker run -d -p 8080:8080 --name=tts zuoban/zb-tts
• Prerequisites: Microsoft Azure Speech Service API key.
• Setup: Docker installation. Access Web UI at http://localhost:8080 or API docs at http://localhost:8080/api-doc.
• Cloudflare Worker: Requires copying a script and setting an API_KEY environment variable.

Highlighted Details

• Supports multiple languages and voices, with configurable speech rate and pitch.
• Offers OpenAI TTS API compatibility, mapping OpenAI voice names to Azure voices.
• Provides both a Web UI and RESTful API for interaction.
• Supports various audio output formats including MP3, WAV, and OGG.

Maintenance & Community

The project is maintained by zuoban. No specific community channels or roadmap details are provided in the README.

Licensing & Compatibility

• License: MIT License.
• Compatibility: Permissive MIT license allows for commercial use and integration into closed-source projects.

Limitations & Caveats

The service relies on an external Microsoft Azure Speech Service API key, which may incur costs. Configuration details for Azure region and API key are essential for operation.