VOICEVOX/voicevox_core

無料で使える中品質なテキスト読み上げソフトウェア、VOICEVOXのコア

What it solves

It provides the core speech synthesis engine for the VOICEVOX ecosystem, allowing developers to integrate high-quality text-to-speech capabilities into their own applications without needing to build the synthesis logic from scratch.

How it works

The project is implemented as a core library available as a C API dynamic library (.so, .dll, .dylib) and a Python API wheel. This allows it to be wrapped or integrated into various programming languages including C++, Python, Go, C#, Ruby, Scala, and Swift via FFI (Foreign Function Interface).

Who it’s for

Developers who want to implement voice synthesis in their software, as well as contributors to the VOICEVOX engine and editor.

Highlights

  • High cross-language compatibility via C and Python APIs.
  • Pre-built libraries available for multiple operating systems.
  • Wide community support with existing wrappers for languages like Ruby, Go, and Swift.

Related

  • Project
    VOICEVOX/voicevox

    A graphical editor for the VOICEVOX speech synthesis system that provides a user-friendly interface for generating AI-driven speech.

  • Project
    VOICEVOX/voicevox_engine

    An HTTP server engine for the VOICEVOX text-to-speech system that enables high-quality speech and singing synthesis via a REST API.

  • Project
    Uberi/speech_recognition

    A Python library that provides a unified interface for speech recognition, supporting multiple online and offline engines like OpenAI Whisper, Google Speech, and Vosk.

  • Project
    brailcom/speechd

    A device-independent interface for speech synthesis that provides a unified API for various Text-to-Speech engines to support accessibility software.

  • Project
    JeremyCCHsu/Python-Wrapper-for-World-Vocoder

    A Python wrapper for the WORLD Vocoder that allows for high-quality speech analysis and resynthesis by decomposing audio into pitch, spectral envelope, and aperiodicity.