B.D. Murphy bf83bb35cc Merge minieq/main: Apache-2.0 LICENSE, NOTICE and SPDX headers
The remote had one commit this branch did not (03f8a85), which adds the
Apache-2.0 LICENSE, the NOTICE and SPDX headers to every .py and .sh
file. The merge was clean - the headers sit at the top of each file and
my changes are further down.

The new files this branch added (languages.py, translations.py, the
cluster package, the new tests and scripts) were written after the
merge base, so the licence commit never saw them. They now carry the
same header, so the convention holds across the whole tree.

Nothing else changed. 883 tests passed / 8 failed - the same 8
pre-existing failures.
2026-11-06 17:12:24 -08:00

UmbraAudio

Quality-first multi-pass audiobook generation from English manuscripts.

Features

  • 5-pass pipeline: Analysis → Voice Design → Mapping → Test → Generate
  • Multi-engine TTS: Chatterbox (primary), Qwen3-TTS (secondary)
  • LLM-enhanced: BookNLP for NLP, LLM for profiling/emotion/pronunciation
  • Web review: FastAPI + HTMX at checkpoints for human approval

Quick Start

python -m umbraaudio.cli init <manuscript.epub> --name 'My Book'
python -m umbraaudio.cli analyze
python -m umbraaudio.cli voices
python -m umbraaudio.cli review

Requirements

  • Python 3.11+
  • NVIDIA GPU with CUDA support (RTX 3060 or better recommended)
  • ffmpeg

Development

pip install -e ".[dev]"
ruff check umbraaudio/
pytest tests/ -v

Commit cadence: commit at least once every Sunday. Never leave a week (let alone a month) of work uncommitted — a single accidental git checkout on 2026-09-20 wiped out a month of changes to umbraaudio/web/routes.py. See AGENTS.md → Commit Cadence.

scripts/commit_check.sh enforces the nudge: it exits non-zero once the tree has been dirty longer than a week. The LaunchAgent com.umbraaudio.commitcheck runs it every Sunday at 18:00 and posts a macOS notification when there is uncommitted work.

scripts/commit_check.sh            # warn if dirty > 7 days
scripts/commit_check.sh --days 3   # tighter threshold
scripts/commit_check.sh --any      # warn on any uncommitted change

Rebuilding from source

The repo tracks source only; large runtime data is reconstructed as needed.

  1. Models: weights are not committed (see .gitignore). Download them:

    bash scripts/download_models.sh   # ~9 GB, targets ./models
    
  2. Qwen3-TTS is a git submodule pinned to upstream commit 022e286:

    git submodule update --init --recursive
    

    The tts_server/web-demo backend includes a local UI customization to qwen_tts/cli/demo.py. It is preserved as a patch — reapply it after checking out the submodule:

    cd Qwen3-TTS && git apply ../scripts/qwen3_tts_demo_umbra_patch.patch
    
  3. Environment: copy/keep .env (contains secrets) and set UMBRA_TTS__* model paths under models/.

Book projects (e.g. DealHunterShip_...) are committed separately under their own project directories and are not part of this program repository.

Description
Quality-first multi-pass audiobook generation pipeline (5-pass: Analysis -> Voice Design -> Mapping -> Test -> Generate). FastAPI+HTMX review UI, Edge-TTS/Qwen3-TTS multi-engine voice, SQLite state.
Readme Apache-2.0 37 MiB
Languages
Python 84.8%
HTML 11.4%
Shell 3%
PLpgSQL 0.7%