# High-Logic/Genie-TTS

GPT-SoVITS ONNX Inference Engine & Model Converter

Repository: https://github.com/High-Logic/Genie-TTS
Canonical: https://ross.abutalabs.com/products/genie-tts
Language: Python
License: MIT
License Family: permissive
Topics: gpt-sovits, tts, text-to-speech, vits, voice-clone, voice-cloning
Last push: 2026-08-03T10:45:00+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 36, longevity 26
- inputs: {"age_days": 373, "days_push": 30, "days_rel": 264, "gap_med": 94, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1754, forks 119 (observed 2026-08-28T04:05:31.904533+00:00)

## What it is
GENIE is a lightweight Python inference engine for the open-source GPT-SoVITS text-to-speech project, optimized for fast CPU-based speech synthesis. It bundles ONNX model conversion, TTS inference, and an API server, supporting Japanese, English, Chinese, and Korean with V2 and V2ProPlus models.

## Use cases
- convert GPT-SoVITS models to ONNX for faster inference
- run text-to-speech on CPU with low latency
- clone a voice and synthesize speech from text
- serve TTS synthesis through an API server
- deploy a lightweight speech synthesis engine with a small runtime footprint
- generate multilingual speech in Japanese, English, Chinese, or Korean

## When to choose
- you need fast, near-real-time TTS inference on CPU without a GPU
- you want a small runtime and model footprint compared to the official PyTorch GPT-SoVITS stack
- you need ONNX conversion of GPT-SoVITS V2 or V2ProPlus models
- you want an easy pip-installable TTS engine with an included API server

## When to avoid
- you need TTS languages outside Japanese, English, Chinese, or Korean
- you require GPT-SoVITS versions other than V2 or V2ProPlus
- you need GPU-optimized or streaming TTS at scale in production
- you want a general-purpose TTS framework rather than a GPT-SoVITS-specific engine

## Facets
- artifact type: library
- maturity: active
- function: tts, llm-inference, machine-learning, http-server
- domain: speech-processing, machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: gpt-sovits, onnx, voice-cloning, speech-synthesis, model-conversion, inference-engine, audio, cpu

## Member repositories
- High-Logic/Genie-TTS (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:31.904533+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 2026-08-30T03:28:02.210181+00:00, confidence not recorded.
  - readme: https://github.com/High-Logic/Genie-TTS (fetched 2026-08-28T04:05:31.904533+00:00, sha c9b2db6b7a99)
- Data as of 2026-08-30T08:39:29.467469+00:00.