Starstruk Logo MarkStarstruk

v1.12.5

NousResearch/hermes-agentv1.12.5Apr 8, 2026by FranckyB

AI Summary

Added Fish Speech S2 Pro TTS engine with multi-language support and inline expression tags, alongside performance optimizations via Triton GPU kernel compilation.

Key Highlights

  • Fish Speech S2 Pro integration (4B parameters, 80+ languages)
  • Support for [tag] syntax for fine-grained speech control
  • Triton/Inductor GPU kernel compilation with persistent caching
  • Windows-specific patches for compilation compatibility

New Features

  • Fish Speech S2 Pro engine in UI
  • TTS model manager methods (get_fish_speech, generate_voice_clone_fish_speech)
  • GPU kernel compilation for Fish Speech acceleration
  • Windows-specific compilation patches

Full Release Notes

Fish Speech S2 Pro Integration and Features:

Added Fish Speech S2 Pro (4B parameter TTS model) as a new engine in the UI, supporting 80+ languages and 15,000+ inline expression tags for fine-grained speech control. The model is auto-downloaded from HuggingFace, and [tag] syntax is supported and automatically stripped for other engines.

The TTS model manager (tts_manager.py) now provides get_fish_speech() and generate_voice_clone_fish_speech() methods, handling model loading, reference audio encoding, kernel cache status reporting, and batch/paragraph generation with all Fish Speech parameters exposed.

Performance and Stability Enhancements:

Implemented Triton/Inductor GPU kernel compilation with persistent caching in models/.cache for Fish Speech, significantly accelerating repeat generations. Added Windows-specific patches for compilation compatibility and informative first-run cache warnings.