Voice
SkillDev toolsSets up spoken replies in the character's own cloned voice, or switches the dub the reference lines are taken from, en, ja, ko or zh, installing the engine's runtime and weights into the plugin's state directory on the first run; with no dub, reports what is installed.
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Voice skill
What this skill tells your AI
The instructions your AI receives, as published by esposter/esposter in packages/genshin-persona/skills/voice/SKILL.md and read by ahel’s review.
node "${CLAUDE_PLUGIN_ROOT}/scripts/genshin.mjs" voice $ARGUMENTS
Relay its lines as written. The first run downloads the engine's runtime and weights — a couple of gigabytes — and prints its progress; it ends by speaking one sentence as this session's character, so the person hears the voice before the first reply does. It also writes the hook that reads each reply's spoken lines into user settings, which the tool reads once per process, so replies are read from the next session.
Signals
- GitHub stars
- 23
- Forks
- 3
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
voice-esposter- Source
- github.com/esposter/esposter