# Setup

Nothing to install. This is a guide repo — read [README.md](README.md) and use [`examples/my-voice/SKILL.md`](examples/my-voice/SKILL.md) as a template.

If you want to follow the corpus-extraction steps in the guide, you'll need:

- [yt-dlp](https://github.com/yt-dlp/yt-dlp) — for pulling audio from your own YouTube videos
- [whisper.cpp](https://github.com/ggml-org/whisper.cpp) or [OpenAI Whisper](https://github.com/openai/whisper) — for local transcription
- A [Claude Skills](https://docs.claude.com/en/docs/agents-and-tools/agent-skills/overview)-compatible environment (Claude Code, claude.ai with Skills enabled, or the Claude API) to actually load and use the skill file you write

None of these are required just to read the guide.