learn-voice
Train RVC voice models from artist names. Full pipeline: YouTube search, download, stem separation, preprocessing, training, and model indexing. Builds a library of singing voices organized by category (voice/instrument).
npx skills add majiayu000/claude-skill-registry --skill learn-voice --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.
# learn-voice Train RVC (Retrieval-based Voice Conversion) models from artist names. Creates a searchable library of singing voices. ## Quick Start - For Agents The simplest way for an agent to learn a voice: ```bash cd /home/graham/workspace/experiments/pi-mono/.pi/skills/learn-voice # Just say who you want to learn ./run.sh learn "Sierra Ferrell" ./run.sh learn "Miles Davis" trumpet ./run.sh learn "Keith Moon" drummer # That's it! The daemon handles everything. ``` ## Agent Workflow When an agent encounters a singer or instrumentalist they want to learn: 1. **Express interest**: `./run.sh learn "Artist Name"` 2. **Daemon trains automatically** (if running) 3. **Use trained voice later** via `create-music` skill ```bash # Agent sees a cool vocalist ./run.sh learn "Yasamin Shahhosseini" # Output: Added to queue: Yasamin Shahhosseini # Queue now has 13 artists # Daemon running (PID 12345) - will train automatically # Later, use the trained voice cd ../create-music ./run.sh rvc-infer --model-name yasamin-shahhosseini --input vocals.wav --output converted.wav ``` ## Manual Training (if needed) ```bash # Train immediately (blocks until done) ./run.sh train "Brennen Leigh" --epochs 200
- Quick Start - For Agents
- Agent Workflow
- Manual Training (if needed)
- Pipeline
- Storage Layout
- Commands
- train
- train-batch
- list
- status
- export
- Quality Gates
- Integration with Other Skills
- discover-music
cd /home/graham/workspace/experiments/pi-mono/.pi/skills/learn-voice Just say who you want to learn Agent sees a cool vocalist Queue now has 13 artists Daemon running (PID 12345) - will train automatically cd ../create-music Train immediately (blocks until done) Batch training Start daemon for continuous training From arguments
What does the learn-voice skill do?
Train RVC voice models from artist names. Full pipeline: YouTube search, download, stem separation, preprocessing, training, and model indexing. Builds a library of singing voices organized by category (voice/instrument).
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill learn-voice --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.