This project provides a Python API wrapper for the CosyVoice2 text-to-speech model, enabling developers to integrate advanced voice synthesis capabilities into their applications. It targets developers and researchers working with AI voice generation, offering flexible options for both built-in voice synthesis and voice cloning.

How It Works

The API exposes several endpoints for different synthesis tasks. The /tts endpoint handles basic text-to-speech with predefined roles (languages/genders). The /clone_eq endpoint performs voice cloning using a reference audio and matching text, while /cone allows cross-lingual voice cloning. It also offers an OpenAI-compatible /v1/audio/speech endpoint for seamless integration with existing OpenAI TTS workflows.

Quick Start & Requirements

• Install Flask: python -m pip install flask
• Run the API: python api.py
• Requires a pre-deployed CosyVoice2 instance.
• Refer to the CosyVoice2 project for core model requirements.

Highlighted Details

• Supports multiple synthesis modes: built-in voices, same-language voice cloning, and cross-lingual voice cloning.
• Provides an OpenAI-compatible API endpoint for easier integration.
• Allows specifying text, reference audio, and reference text for cloning.

Maintenance & Community

• Project maintained by jianchang512.
• No explicit community links (Discord, Slack) or roadmap are provided in the README.

Licensing & Compatibility

• The README does not specify a license.
• Compatibility for commercial use or closed-source linking is undetermined without a license.

Limitations & Caveats

The project relies on a pre-existing CosyVoice2 deployment, and its own licensing is not specified, which may impact commercial adoption. The README does not detail error handling or advanced configuration options.