Remove Use AI enhancement toggle — always use AI for character extraction since Qwen3-TTS is the default engine

Fix: remove extract_status from Clear button outputs to avoid UnboundLocalError

Polish pass: add File download for ZIP support, Clear button, sample load updates stats/chapters, GPU detection cleanup, character descriptions persist in save/load, long-text warnings, first-run notes on Generate tab.

Add first-run model download note to About tab.

Robust GPU detection: TTSEngine checks torch.cuda.is_available() at model load time, with CPU-safe float32 fallback.

Update README with current feature set: Quick Generate modes, AI-by-default, chapter detection, multi-format export.

Quick Generate: add full mode selector (preset/clone/design) for narrator voice on Story tab.

AI-by-default: narrator and characters default to design mode. AI enhancement checkbox defaults ON. AI extraction returns voice descriptions. Fix load project output count.

Fix checkbox checked-state visibility in dark theme. Expand Character Voices help text to highlight Preset/Clone/Design modes.

Fix generation bug: correct positional arg mapping for Quick Generate, main Generate, Save/Load. Add *args unpacking for 80 character inputs.

Major enhancement: file upload, chapter detection, segment previews, multi-format export, speed control, project save/load, quick generate, sample stories

Fix CSS contrast for checkbox labels, lists, and code elements

Add .gitignore and remove pycache

Add ZeroGPU spaces.GPU decorators and local fallback for GPU functions

Fix README frontmatter: valid colors and short desc length

Initial deploy: AudioBook Forge with Qwen3-TTS backend, character voice mapping, and dark Gradio UI

initial commit