v1.12.5

FranckyB/Voice-Clone-Studiov1.12.5Apr 8, 2026by FranckyB

AI Summary

This release introduces Fish Speech S2 Pro as a new TTS engine with 4B parameters supporting 80+ languages and 15,000+ expression tags. It also adds Triton/Inductor GPU kernel compilation with persistent caching for significantly faster repeat generations.

Key Highlights

Fish Speech S2 Pro integration as new TTS engine with 4B parameters
Support for 80+ languages and 15,000+ inline expression tags
Auto-download from HuggingFace with [tag] syntax support
TTS model manager methods for Fish Speech (get_fish_speech, generate_voice_clone_fish_speech)
Triton/Inductor GPU kernel compilation with persistent caching in models/.cache
Windows-specific patches for compilation compatibility and first-run cache warnings

New Features

Fish Speech S2 Pro TTS engine
GPU kernel compilation caching
Reference audio encoding for Fish Speech
Batch/paragraph generation with all Fish Speech parameters

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.