Plachtaa/VITS-fast-fine-tuning

Health v2 · maintenance only

Flags: archived

Adoption not part of the score

5012 stars · 727 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A Python pipeline for fast fine-tuning of VITS text-to-speech models, enabling speaker adaptation in under an hour from short audio, long audio, or video samples. It supports multilingual (English, Japanese, Chinese) TTS synthesis and many-to-many voice conversion between added and preset speakers.

Use cases

• clone a character voice from a few short audio clips
• fine-tune a TTS model on my own voice
• convert voice between multiple speakers
• synthesize Chinese Japanese or English speech with custom voices
• extract voice from videos for TTS training
• train a voice model on Google Colab

When to choose

• you want to add custom voices to a pretrained VITS TTS model quickly
• you need many-to-many voice conversion between speakers
• you have limited training data (10+ short clips or 3+ minutes of audio)
• you want multilingual TTS in English, Japanese, and Chinese

When to avoid

• you need production-grade, low-latency TTS serving at scale
• you want to train a TTS model from scratch rather than fine-tune
• you need languages beyond English, Japanese, and Chinese
• you require real-time voice conversion with minimal latency

Facets

library · maturity active

tts machine-learning llm-training audio-processing speech-recognition speech-processing machine-learning deep-learning artificial-intelligence python cross-platform windows vits voice-conversion voice-cloning fine-tuning text-to-speech speaker-adaptation transfer-learning audio gpu web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Plachtaa/VITS-fast-fine-tuning")