Raise Modal generation timeout to 2 hours

Lower batching gate to 250 words; split monologues into even atomic pieces

Sentence-split oversized turns so solo monologues can batch

Fix stale cache hits: order-sensitive speaker key + cache version bump

Modal backend: accept a per-speaker uploaded voice clone

Rebuild frontend as FastAPI + hand-built UI, replacing Gradio

Add AI script generator, conversation editor, and cleanup

Modify feeback comps and checks.

Added feedback to UI for inference

Add real-time progress streaming from Modal to UI

Fix: Modal deprecation warning and HF authentication

Fix: Modal deprecation warning and HF authentication

Fix Missing UI comps

Fix: Update add_local_dir paths in modal_runner.py

Exclude backend_modal from Hugging Face Space deployment

Refactor: Separate frontend and backend code