v1.12.5

yukangcao/DreamAvatarv1.12.5Apr 8, 2026by FranckyB

AI Summary

Integrates the Fish Speech S2 Pro (4B parameter) TTS model, offering support for 80+ languages and 15,000+ inline expression tags, along with significant compilation speed-ups.

Key Highlights

Added Fish Speech S2 Pro as a new engine supporting 80+ languages and 15,000+ tags
Implemented Triton/Inductor GPU kernel compilation with persistent caching for faster generations
Added model manager methods for loading and generating voice clones
Included Windows-specific patches for compilation compatibility

New Features

Fish Speech S2 Pro engine integration
GPU kernel compilation with caching
TTS model manager API

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.