Feature parity with original Blocks UI

Mobile + tablet responsive layout

Unified script stage + advanced settings + refined design language

Replace waveform with highlighted lyrics, condense controls, drop channel strip

Video-studio layout: audio viewport dominates the screen

Pure DAW layout with word-by-word script highlight

Garageband + ChatGPT-style UI

Prune UI to studio essentials

Add professional channel strip to UI

Redesign UI as a professional DAW-style audio studio

Serve / as HTMLResponse so the browser renders it

Add editdistance + remaining [tts]-extra deps

Pre-install the full NeMo [tts] dep graph at build time

Add matplotlib (NeMo TTS losses runtime dep)

Pin tokenizers to transformers 5.3.0's accepted range

Pre-add tokenizers (transformers 5.x runtime dep)

Add regex to requirements (transformers 5.x runtime dep)

Move nemo-toolkit install to runtime to unblock gradio 6.20 build

Upgrade gradio to 6.20

Convert to gradio.Server backend with custom HTML frontend

Update speaker list

Change speakers list

Make final list of speakers

Update README.md

Update config.yaml

Swap example voices: Tony->Sean (Boston chat), Sofía->Diego (Spanish)

Shorten example phrases (~8-10s); neutral Sofía line, drop Tony's "capisce"

Expand preset roster to 18 multilingual voices with labeled examples

Simplify header subtitle

Trim generation UI: cap sliders, slimmer styling, drop stop-threshold

Length-gate text-CFG, hide CFG knobs, cap max_frames

Add preset examples table at page bottom

Restore Generated speech label on output audio

Hide redundant/button-like field labels in UI

Button to the right side

Update README.md

fix deps 1

init

initial commit