# PlayVoice/vits_chinese

Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!

Repository: https://github.com/PlayVoice/vits_chinese
Canonical: https://ross.abutalabs.com/products/vits_chinese
Homepage: https://huggingface.co/spaces/maxmax20160403/vits_chinese
Language: Python
License: MIT
License Family: permissive
Topics: tts, vits, naturalspeech, bert, bert-vits, aishell3, bert-vits2
Last push: 2024-02-05T03:54:40+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1801, "days_push": 940, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1227, forks 173 (observed 2026-08-28T04:04:03.347862+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: tts, machine-learning, deep-learning, audio-processing, llm-inference
- domain: speech-processing, machine-learning
- platform: python, cross-platform
- tags: vits, bert, chinese-tts, speech-synthesis, onnx, streaming-audio, naturalspeech, natural-language-processing, audio

## Member repositories
- PlayVoice/vits_chinese (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:03.347862+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 2026-08-30T06:15:13.812569+00:00, confidence not recorded.
  - readme: https://github.com/PlayVoice/vits_chinese (fetched 2026-08-28T04:04:03.347862+00:00, sha 8c433d75fcde)
  - homepage: https://huggingface.co/spaces/maxmax20160403/vits_chinese (fetched 2026-08-29T12:23:11.103858+00:00, sha 92106ae0e900)
- Data as of 2026-08-30T08:39:29.467469+00:00.