fix to ui to visible

Fix record button

perf: improve LFM2.5-Audio inference quality and reliability

perf: warmup generation, async LFM loading, reduce max_new_tokens

fix: proper Mimi decode on HF Space — only disable dynamo on Windows, explicit device handling

fix: Play produces no sound — switch to streaming audio + system deps

fix: Play produces no sound on HF Space

refactor: consolidate to Base 1.7B only, remove CustomVoice

fix: audio decode normalization + warmup first 5 paragraphs

feat: show paragraph progress during Play + warmup first paragraphs at startup

ui: hide chunk/queue processing details from user during Play

feat: auto-start mic recording on Ask click (100ms user gesture window)

fix: add stop_recording JS fallback to auto-submit Q&A

fix: dedup only on auto-submit, manual Get Answer always works

fix: convert Path to str for wave.open (Python 3.13 compat)

feat: bounded pre-gen, cancellation, disk cache pruning, GPU lock

refactor: runtime config, Q&A flow module, storage paths, and cleanup

perf: 5 latency optimizations for TTS playback

feat: enable FlashAttention-2 for all models via runtime install + SDPA fallback

rename: app.py -> app_cascade.py, app_lfm.py -> app.py

fix: auto-submit - JS clicks submit 500ms after stop_recording + .change backup

fix: auto-submit Q&A - stop_recording + change + JS fallback click

ui: remove text input box from Q&A - voice only

fix: remove trigger word, always auto-submit on recording stop

feat: trigger phrase 'answer me' to generate Q&A answer

fix: auto-submit question - use .change() instead of .stop_recording()

fix: voice cloning playback - add status indicator, fallback, debug logging

fix: voice cards clickable - select cloned voice as narrator

fix: pause retains position, Ask pauses play, auto-start mic, hide Q&A during play

fix: pause playback on Ask click and tab switch (Explore/Clone)

fix: Resume button - show Ask btn again, clear audio, add question_audio output

perf: preload all models at startup, improve Q&A context and auto-submit

feat: voice-first Q&A with auto-submit and autoplay answer

fix: Ask voice question - null handling, answer visibility

fix: remove custom dtype/attn params to fix CUDA assert on T4

fix: CUDA assert on T4 GPU - use eager attention, disable torch.compile

fix: replace Supertonic with Qwen3-TTS 0.6B CustomVoice, fix Play button

feat: persist voice profiles to Voice_Profile/ with auto-load on startup

fix: move CSS from Blocks constructor to launch() for Gradio 6.0

refactor: remove dead UI elements, tighten model integration

feat: implement real voice cloning with Qwen3-TTS (sprint step 3)

fix: XSS sanitization, per-request audio files, soundfile-based ASR

feat: wire Whisper-small ASR and Qwen2.5-3B Q&A into app (sprint steps 9-10)

feat: integrate Supertonic TTS with sentence-level chunk streaming

fix gradio version 5.33 for compatibility

fix bug of image path traversal

feat: full story text display with paragraph highlight on slider

feat: merge Library + Player into single tab with click-to-play

feat: replace Unsplash cover URLs with local assets/covers/ PNG paths

Load book list dynamically from stories/ folder