tts-horus
This skill standardizes the end-to-end Horus voice workflow using uvx-style
npx skills add majiayu000/claude-skill-registry --skill tts-horus-grahama1970-agent-skills --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
--- name: tts-horus description: > Build and operate the Horus TTS pipeline from cleared audiobooks. Includes dataset prep, WhisperX alignment, XTTS training, voice coloring, and persona inference helpers. allowed-tools: Bash, Read triggers: - horus tts - build horus voice - voice coloring - tts pipeline metadata: short-description: Horus TTS dataset + training + inference pipeline provides: - tts-horus composes: [, task-monitor] --- # 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. ```bash # 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 # Step 2: Extract clips (CPU-bound, uses ffmpeg) python run/tts/extract_clips.py \ --segments datasets/horus_voice/segments_merged.jsonl \ --audio persona/dat
- Commands
- dataset
- align
- train
- say
- server
- color
- Notes
- Gotchas
- Learning Rate Schedule
- Automated Pipeline
- Current Status (2026-01-23)
Step 1: Transcribe and segment python run/tts/ingest_audiobook.py \ Step 2: Extract clips (CPU-bound, uses ffmpeg) python run/tts/extract_clips.py \ python run/tts/align_transcripts.py \ python run/tts/train_xtts_coqui.py --config configs/tts/horus_xtts.yaml python run/tts/say.py "Lupercal speaks." python run/tts/server.py python run/tts/color_voice.py --base horus --color warm --alpha 0.4 Start extraction, then auto-train when complete
What does the tts-horus skill do?
This skill standardizes the end-to-end Horus voice workflow using uvx-style
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill tts-horus-grahama1970-agent-skills --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.