terrancemoon9/Boovore_Multi-Engine-TTS-Studio

docs: update README for 6-engine Voxtral release

feat: add Voxtral TTS engine + French prosody preprocessing

Fix Voice Design voice consistency: anchor-based cloning

Fix F5-TTS crash on HF Space: NoneType ref_path when no audio uploaded

Fix 3 real bugs found in full code audit

Fix Voice Design voice consistency: full RNG determinism for seed

Add interactive book reader with start/end selection + improved chapter detection

Add visible warning when Qwen3 Voice Design is selected without loaded model

Implement Rolling Reference technique for Fish-Speech voice consistency

Fix 3 bugs found in full code audit

Improve audiobook narration quality based on pro narrator techniques

Add expressive mode checkbox for audiobook narration

Fix audiobook voice consistency + add Fish-Speech named presets

Enable torch.compile for Fish-Speech on GPU (2-3x speedup)

Fix: never sys.exit on missing faster_qwen3_tts — server starts regardless

Restore HuggingFace Space YAML frontmatter in README

Add CPU/GPU selection via ENABLED_ENGINES env var, document in README

Update README.md

Add UI screenshot to README

Add engine gating, CPU/HF Space support, multi-lang Kokoro, and expanded UI params

Add global TTS language selector + more params for Chatterbox & F5-TTS

Fix Qwen3 Voice Design redirect bug + Fish audiobook optimizations

Improve Qwen3-TTS: auto-status, Voice Design presets, more languages

Add HuggingFace Space metadata to README

Add engine params (speed/CFG/ref_text), fix dropdown colors, add FR/EN toggle

Add 13 Kokoro voices, improve audiobook UX + chapter detection

README: translate to English

Boovore: full UI redesign + Fish-Speech engine + GitHub prep

Remove binary ref wav from git tracking

Add XTTS narrator FR mode: server proxy, UI row, launch scripts

Auto-uncheck front matter (publisher/title/author) before first real chapter

Improve audiobook: ETA, auto-DL, retry, pause/resume, merge, format titles

Set 0.6B-Base as default model

Add PDF and EPUB support for audiobook tab

Add time estimation and Audiobook tab

Increase text and audio generation limits for longer tests

fix(demo): don't switch uploads to Simple mode

fix(demo): default clone toggle to Advanced (ICL) mode

fix(demo): prevent stale preset from overriding browser recordings in ICL mode

Add audio size limit (10 MB / ~1 min) and restore text length guard

Add 1000-char text limit to prevent CUDA static cache overflow

Fix stale model ref race, add ACTIVE_MODELS env var, hide unavailable modes

Fix permission error for preset assets and PyTorch cache dir in HF Spaces

Make model cache size configurable via MODEL_CACHE_SIZE env var (default 2, Space uses 5)

Cache all loaded models (LRU, max 5) to avoid re-capture on model switch

Serialize generation with asyncio.Lock and show queue position to users

Center header and content together as a unit in viewport

Center app content vertically in viewport

Download preset wav files from GitHub at startup instead of bundling them

Move preset buttons left of play, match ref-chip height