# Artrajz/vits-simple-api

A simple VITS HTTP API, developed by extending Moegoe with additional features.

Repository: https://github.com/Artrajz/vits-simple-api
Canonical: https://ross.abutalabs.com/products/vits-simple-api
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: bert-vits2, tts, vits, moegoe, gpt-sovits, tts-api
Last push: 2026-05-18T10:29:11+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 83, release rhythm 40, longevity 90
- inputs: {"age_days": 1270, "days_push": 107, "days_rel": 576, "gap_med": 18, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1052, forks 135 (observed 2026-08-28T04:03:23.474459+00:00)

## What it is
A Python HTTP API service that exposes VITS-family text-to-speech models (VITS, Bert-VITS2, GPT-SoVITS, W2V2 emotional VITS) for inference. It supports multiple model loading, automatic language detection, long-text batching, GPU acceleration, and Docker deployment.

## Use cases
- serve text-to-speech over http api
- deploy vits tts model as a rest service
- convert text to speech with bert-vits2
- host gpt-sovits voice cloning api
- add tts to a chatbot or vtuber app
- batch synthesize long text to audio

## When to choose
- you want a self-hosted HTTP TTS API supporting multiple VITS model types
- you need Docker deployment with GPU inference
- you need multi-speaker, multi-model, or emotional TTS via simple GET requests

## When to avoid
- you only need a GUI desktop TTS tool
- you need production-grade scalable speech service with enterprise support
- you want cloud-managed TTS without hosting models yourself

## Facets
- artifact type: service
- maturity: active
- function: tts, http-server, speech-recognition, machine-learning, llm-inference
- domain: speech-processing, artificial-intelligence, apis
- platform: python, self-hosted
- tags: vits, bert-vits2, gpt-sovits, voice-conversion, ssml, text-to-speech-api, moegoe, audio, docker, linux, gpu, web-server

## Member repositories
- Artrajz/vits-simple-api (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:23.474459+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:59:40.200995+00:00, confidence not recorded.
  - readme: https://github.com/Artrajz/vits-simple-api (fetched 2026-08-28T04:03:23.474459+00:00, sha 0e0ad1a839ba)
- Data as of 2026-08-30T08:39:29.467469+00:00.