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

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

perf: 4-chunk pre-buffer + batch into ~5s audio blocks

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

perf: reduce TTS latency - shorter chunks + sub-segment streaming

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

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

docs: update README - reflect Qwen3-TTS, voice-first Q&A, all current features

fix: voice cards clickable - select cloned voice as narrator

revert: voice cloning back to GPU - user will use larger GPU

fix: voice cloning OOM on T4 - load 1.7B Base model on CPU

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

docs: update Space metadata (title, SDK version)

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

docs: update sprint.md with progress summary and remaining tasks

test: add comprehensive integration test suite (74 tests)

refactor: remove dead UI elements, tighten model integration

perf: add TTS latency optimizations

docs: update all docs to reflect Qwen3-TTS architecture

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)

Merge origin/master: adopt gradio==5.33.0 compatibility fix

Update sprint.md: mark completed tasks through Day 2 morning

Merge HuggingFace_Hack/main: real TTS pipeline + asset overhaul

Merge pull request #7 from MomsVoiceAI/fix/hf-bug

bumpup gradio 5.35 for font issue

add requirement for supertonic

fix: add quoted sdk_version and python_version to HF Space README

commit README for hf space

Merge pull request #3 from MomsVoiceAI/frontend/gradio-ui

chore: revert .gitattributes to filter=lfs (git-xet is an LFS transfer agent)

chore: switch binary tracking from LFS to Xet for HuggingFace

feat: integrate Supertonic TTS with sentence-level chunk streaming

Merge pull request #4 from MomsVoiceAI/fix/image-path

Merge pull request #4 from MomsVoiceAI/fix/image-path

fix gradio version 5.33 for compatibility

fix gradio version 5.33 for compatibility

fix bug of image path traversal

fix bug of image path traversal

chore: add HF Space yaml header to README.md