PlayVoice/vits_chinese

Health v2 · maintenance only

Adoption not part of the score

1227 stars · 173 forks observed · 2026-08-28

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

A Chinese text-to-speech library combining VITS with BERT-based prosody embeddings and NaturalSpeech infer-loss features, supporting ONNX chunked streaming output. It is primarily an educational project for learning TTS algorithms rather than a production-ready system.

Use cases

• generate chinese speech from text
• train a chinese tts model
• stream tts audio in chunks with onnx
• learn how vits and bert prosody work
• fine-tune a tts model with infer loss
• build a voice assistant with chinese speech synthesis

When to choose

• you want to study or experiment with modern TTS architectures like VITS and BERT prosody
• you need Chinese speech synthesis with natural prosody and streaming output
• you want a lightweight MIT-licensed TTS codebase to modify

When to avoid

• you need a production-grade, well-supported TTS system
• you need non-Chinese language support
• you want a maintained product with active releases and support

Facets

library · maturity maintenance

tts machine-learning deep-learning audio-processing llm-inference speech-processing machine-learning python cross-platform vits bert chinese-tts speech-synthesis onnx streaming-audio naturalspeech natural-language-processing audio

Member repositories

For agents

markdown · JSON · MCP: product_card(name="PlayVoice/vits_chinese")