Starstruk Logo MarkStarstruk

v1.12.5

gristlabs/grist-corev1.12.5Apr 8, 2026by FranckyB

AI Summary

This release focuses on integrating the Fish Speech S2 Pro model, supporting 80+ languages and 15,000+ inline expression tags, and implementing GPU kernel compilation with persistent caching for performance improvements.

Key Highlights

  • Integration of Fish Speech S2 Pro (4B parameter) TTS model.
  • Support for 80+ languages and 15,000+ inline expression tags.
  • Triton/Inductor GPU kernel compilation with persistent caching.
  • Windows-specific patches for compilation compatibility.

New Features

  • New `get_fish_speech()` and `generate_voice_clone_fish_speech()` methods in TTS manager.
  • Model loading and reference audio encoding handling.
  • Batch and paragraph generation with exposed Fish Speech parameters.
  • Persistent kernel caching in models/.cache.

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.