jaywalnut310/vits

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

7889 stars · 1381 forks observed · 2026-08-28

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

VITS is the official PyTorch implementation of an end-to-end text-to-speech model based on a conditional variational autoencoder with adversarial learning and normalizing flows. It supports single-speaker and multi-speaker training, voice conversion, and provides pretrained models for speech synthesis.

Use cases

• synthesize speech from text
• train a text-to-speech model on my own dataset
• generate natural sounding voice audio
• convert one voice to another
• run a multi-speaker TTS model
• reproduce a research TTS baseline

When to choose

• you need high-quality end-to-end TTS with parallel sampling
• you want to train or fine-tune a TTS model on custom data
• you need a research-grade TTS baseline with pretrained checkpoints

When to avoid

• you need a production-ready, actively maintained TTS service
• you want a simple pip-installable inference library
• you lack GPU resources for training

Facets

library · maturity maintenance

tts machine-learning deep-learning audio-processing speech-processing deep-learning artificial-intelligence python text-to-speech speech-synthesis pytorch variational-autoencoder adversarial-training research-code pretrained-models linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="jaywalnut310/vits")