GP

GPT-SoVITS

Few-shot voice cloning and text-to-speech

Self-Hosted AI ★ 60.6k stars Hard setup MIT

GPT-SoVITS is an open-source voice conversion and text-to-speech system capable of cloning a voice from a very short audio sample. It can be self-hosted with a web UI for training and generating speech in multiple languages.

Key features

  • Few-shot voice cloning
  • Multilingual synthesis
  • Web training UI
  • Runs locally

Pros & cons

Strengths

  • Released under the MIT license
  • First-class Docker support for quick deployment
  • Mature project with 60.6k GitHub stars
  • Written in Python

Trade-offs

  • GPU strongly recommended
  • Setup complexity

GPT-SoVITS replaces

Compare GPT-SoVITS

34 head-to-head comparisons.

Similar self-hosted ai apps