Starstruk Logo MarkStarstruk

v2.0

chaitin/SafeLinev2.0Mar 31, 2026by lipku

AI Summary

Major version 2.0 refactor reorganizing code structure and implementing a plugin-based architecture for models and TTS.

Key Highlights

  • Code refactoring: moved digital human models and audio features to the avatars directory
  • Adopted plugin-based architecture for digital human models, TTS, and transmission methods
  • Integrated common inference and response logic into BaseAvatar
  • Integrated audio feature segmentation logic into BaseAsr
  • Stream output logic moved to streamout directory with RTMP output support

New Features

  • RTMP output support
  • Aliyun qwentts integration

Full Release Notes

1，重构代码，数字人模型和音频特征代码移到avatars目录下
2，数字人模型、tts、传输方式改成plugin方式接入
3，传输方式整理成单独的类，放到streamout目录下，添加rtmp输出
4，数字人推理和回贴公共部分代码整合到BaseAvatar中，各模型只需要实现自己特有部分代码
5，音频特征的切分代码整合到BaseAsr中
6，tts添加阿里云qwentts