Starstruk Logo MarkStarstruk

v2.0

ruixenui/ruixen.comv2.0Mar 31, 2026by lipku

AI Summary

Major refactoring moving digital human models and audio features to the avatars directory, switching TTS and transmission to a plugin architecture, and adding RTMP output support.

Key Highlights

  • Code refactoring to avatars directory
  • Plugin-based TTS and transmission
  • RTMP output stream support
  • Consolidation into BaseAvatar and BaseAsr classes
  • Aliyun QwenTTS integration

New Features

  • Directory restructuring for models and audio
  • Plugin architecture for TTS and transmission
  • RTMP stream output
  • Base classes for Avatar and ASR logic
  • Aliyun QwenTTS support

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