CjangCjengh/MoeGoe

Health v2 · maintenance only

Adoption not part of the score

2423 stars · 242 forks observed · 2026-08-28

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

MoeGoe is an executable command-line tool for running inference with VITS text-to-speech models, supporting TTS, voice conversion, HuBERT-VITS, and W2V2-VITS with emotional reference audio. It is written in Python and distributed as a ready-to-run executable.

Use cases

• generate speech audio from text using a VITS model
• convert an audio clip to sound like a different speaker
• run voice conversion with HuBERT-soft features
• synthesize speech with emotion control via a W2V2 emotion model
• batch-generate anime character voice lines locally

When to choose

• you have a trained VITS model and want a simple offline inference tool
• you need voice conversion between speakers without writing code
• you want a lightweight executable instead of a full ML pipeline

When to avoid

• you need to train or fine-tune VITS models
• you want a GUI (use the companion MoeGoe_GUI instead)
• you need production-grade streaming TTS APIs

Facets

cli-tool · maturity maintenance

tts speech-recognition audio-processing machine-learning llm-inference speech-processing machine-learning artificial-intelligence windows cross-platform python cli vits voice-conversion text-to-speech hubert inference anime-voice audio

Member repositories

For agents

markdown · JSON · MCP: product_card(name="CjangCjengh/MoeGoe")