v1.12.5

enricoros/big-AGIv1.12.5Apr 8, 2026by FranckyB

AI Summary

This release integrates the Fish Speech S2 Pro TTS model with expanded language support, alongside performance optimizations via GPU kernel compilation and persistent caching.

Key Highlights

Adds Fish Speech S2 Pro (4B parameter) engine
Supports 80+ languages and 15,000+ inline expression tags
Implements Triton/Inductor GPU kernel compilation with caching
Includes Windows-specific compilation patches

New Features

Fish Speech S2 Pro TTS engine
TTS model manager methods
GPU kernel compilation
Persistent caching for models

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.