fishaudio/Bert-VITS2

vits2 backbone with multilingual-bert

What it solves

It provides a text-to-speech (TTS) system that combines the VITS2 backbone with multilingual BERT embeddings to improve speech synthesis quality and naturalness.

How it works

The project implements a VITS2 architecture integrated with a multilingual BERT model to process text input and generate high-quality audio output. It draws core ideas from MassTTS and builds upon existing VITS-based frameworks.

Who it’s for

Developers and AI researchers interested in training and deploying high-quality, multilingual text-to-speech models.

Highlights

  • Multilingual BERT integration for better text representation.
  • Based on the VITS2 backbone for efficient speech synthesis.
  • Includes a preprocessing guide via webui_preprocess.py.

Related

  • Project
    fishaudio/fish-speech

    A state-of-the-art multilingual text-to-speech system that uses a Dual-AR architecture to provide realistic voice cloning and fine-grained emotional control via natural language tags.

  • Project
    Zyphra/ZONOS2

    ZONOS2 is a high-fidelity, multilingual text-to-speech model using a Mixture-of-Experts backbone to deliver naturalistic voice cloning and expressive emotional control.

  • Project
    SWivid/F5-TTS

    F5-TTS is a high-performance text-to-speech system using a Diffusion Transformer and flow matching to generate fluent, faithful speech with fast training and inference.

  • Project
    VOICEVOX/voicevox_engine

    VOICEVOX Engine is an open‑source HTTP server that wraps the VOICEVOX Japanese TTS core. It lets you send text (or a detailed synthesis query) via REST endpoints and receive WAV audio, with support for streaming, user dictionaries, presets, voice morphing, singing synthesis, and optional GPU acceleration. Docker images and a mock mode make deployment easy, and the API is documented at /docs.