Horus TTS Pipeline

This skill standardizes the end-to-end Horus voice workflow using uvx-style invocations so dependencies are isolated per command. It assumes recordings live under persona/data/audiobooks/ with per-book clean/ folders.

Commands

dataset

Builds the Horus dataset from Horus Rising using faster-whisper segmentation.

# Step 1: Transcribe and segment
python run/tts/ingest_audiobook.py \
  --audio persona/data/audiobooks/Horus_Rising_The_Horus_Heresy_Book_1-LC_64_22050_stereo/audio.m4b \
  --book-name Horus_Rising \
  --output-dir datasets/horus_voice \
  --max-hours 0