High-Logic/Genie-TTS

Health v2 · maintenance only

Adoption not part of the score

1754 stars · 119 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity active

tts llm-inference machine-learning http-server speech-processing machine-learning artificial-intelligence python cross-platform gpt-sovits onnx voice-cloning speech-synthesis model-conversion inference-engine audio cpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="High-Logic/Genie-TTS")