菜单
Local text-to-speech via sherpa-onnx. Fully offline, no cloud dependency, supports multiple voice models across platforms.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/yunseo-kim/agent-toolbox --skill sherpa-onnx-tts命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Set up, improve, or audit analytics tracking with GA4, GTM, event naming conventions, and conversion measurement
Build multi-component HTML artifacts using React, Tailwind CSS, and shadcn/ui. Use for complex interactive artifacts requiring state management, routing, or component libraries, not for simple single-file HTML/JSX artifacts.
Create competitor comparison and alternative pages for SEO and sales enablement with differentiated positioning
正在显示 SKILL.md
基于 SOC 职业分类
| name | sherpa-onnx-tts |
| description | Local text-to-speech via sherpa-onnx. Fully offline, no cloud dependency, supports multiple voice models across platforms. |
| license | Sustainable Use License 1.0 |
| metadata | {"domain":"content-media","subdomain":"media-processing","tags":"tts, text-to-speech, local, offline, onnx","author":"Yunseo Kim <dev@yunseo.kim>","lastUpdated":"12026-02-16","provenance":"adapted"} |
Local TTS using the sherpa-onnx offline CLI.
~/.the assistant/tools/sherpa-onnx-tts/runtime)~/.the assistant/tools/sherpa-onnx-tts/models)Update ~/.the assistant/the assistant.json:
{
skills: {
entries: {
"sherpa-onnx-tts": {
env: {
SHERPA_ONNX_RUNTIME_DIR: "~/.the assistant/tools/sherpa-onnx-tts/runtime",
SHERPA_ONNX_MODEL_DIR: "~/.the assistant/tools/sherpa-onnx-tts/models/vits-piper-en_US-lessac-high",
},
},
},
},
}
The wrapper lives in this skill folder. Run it directly, or add the wrapper to PATH:
export PATH="{skillDir}/bin:$PATH"
{skillDir}/bin/sherpa-onnx-tts -o ./tts.wav "Hello from local TTS."
Notes:
tts-models release if you want another voice..onnx files, set SHERPA_ONNX_MODEL_FILE or pass --model-file.--tokens-file or --data-dir to override the defaults.node {skillDir}\\bin\\sherpa-onnx-tts -o tts.wav "Hello from local TTS."