Agent Skills
› leemysw/yovoice
› yovoice-voice
yovoice-voice
GitHub提供语音设置技能，支持通过update_work调整音色、情感、速度等参数。根据modelId前缀匹配模型并读取对应参考文档，确保参数设置的准确性与兼容性。
触发场景
用户想要改变语音的听感
用户需要调整模型的语音参数
安装
npx skills add leemysw/yovoice --skill yovoice-voice -g -y
SKILL.md
Frontmatter
{
"name": "yovoice-voice",
"description": "Voice settings in the right-hand inspector of text and story works (model, voice source, voice design, emotion, speed, sampling, modelOptions), per model. Use when the user wants to change how a voice sounds or tune a model's parameters."
}
Voice settings (声音设置)
Everything in the inspector is edited with update_work {"id","settings":{...}}; only given fields change, and out-of-range values are rejected with the reason. For one story speaker use speakerSettings [{"speaker","settings":{...}}].
Fields, ranges, voice-source modes and modelOptions differ per model. Read only the reference for the work's model, references/<name>.md in this skill's directory (from the workspace: .agents/skills/yovoice-voice/references/<name>.md), found by the prefix of its modelId (get_work):
| modelId prefix | name |
|---|---|
index- |
indextts |
omnivoice- |
omnivoice |
qwen3-tts- |
qwen3-tts |
voxcpm2- |
voxcpm2 |
breeze-tts- |
breeze |
ming3-tts- |
ming3_tts |
voxtral-tts- |
voxtral_tts |
plapre- |
plapre |
xtts-v2- |
xtts_v2 |
gradium-phonon- |
gradium_phonon |
fish-drama3- |
fish_drama3 |
kokoro- |
kokoro |
When switching the work to another model, read that model's reference before setting its fields; fields the new model does not use are ignored.
版本历史
- 35d091f 当前 2026-11-02 09:02
