闲社服务运行正常AI智能体自动化平台
客户端下载帮助中心服务商入驻
免费注册
技能集市 > AI智能 > ningyao-voice-launcher
n

宁瑶语音启动器

技能标识：ningyao-voice-launcher

Install and configure a local browser-based Chinese voice chat launcher with the Ning Yao persona, including one-click Windows launchers, browser speech I/O, screen awareness, and a safe terminal panel. Use when the user wants a local voice companion, a persona-tuned voice chat setup, or help packaging/deploying the Ning Yao voice launcher.

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 0.1.0
检测标记
后台标记通过
免费
免费获取
0
收藏
来源与检测标记为平台登记信息，并不代表已展示可复核的检测报告。使用前请核对版本、依赖和所需权限，建议先在隔离环境中运行。
概述
安装方式
版本历史

宁瑶语音启动器

Ningyao 语音启动器

将捆绑的启动器安装到用户选择的文件夹中，然后配置 .env 文件并运行。

工作流程

  1. 1. 将 assets/voice-chat-local 复制到目标文件夹。
  2. 在复制的文件夹中运行 npm install 安装依赖。
  3. 将 .env.example 复制为 .env 并填写 OPENAIAPIKEY。
  4. 通过 start-voice-chat.cmd 或 start-voice-chat-bg.cmd 启动。

捆绑文件

  • - assets/voice-chat-local：浏览器语音聊天应用模板。
  • scripts/install-launcher.ps1：Windows 安装/复制辅助脚本。

Windows 安装

运行：

powershell
powershell -ExecutionPolicy Bypass -File scripts/install-launcher.ps1 -Destination $env:USERPROFILE\Desktop\ningyao-voice-chat

安装程序会复制模板，跳过 .env 文件，并可选择运行 npm install。

配置

在 .env 中设置以下内容：

  • - OPENAIAPIKEY：必填
  • OPENAIBASEURL：可选的 API 兼容端点
  • OPENAIMODEL：如需屏幕分析，需使用支持文本和视觉的模型
  • OPENAITIMEOUTMS：请求超时时间
  • PORT：本地端口
  • SYSTEMPROMPT：角色提示词

注意事项

  • - 建议使用 Chrome 或 Edge 浏览器以获得语音识别和语音合成支持。
  • 终端面板被有意限制为较小的白名单。
  • 如果启用屏幕分析，请选择支持图像输入的模型。

标签

skill ai

通过对话安装

以下为平台配置的接入选项，并非逐项实测通过。能否安装取决于客户端支持、技能来源和运行环境：

OpenClaw WorkBuddy QClaw Kimi Claude

方式一：安装 SkillHub 和技能

帮我安装 SkillHub 和 ningyao-voice-launcher-1776120138 技能

方式二：设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源，然后帮我安装 ningyao-voice-launcher-1776120138 技能

通过命令行安装

skillhub install ningyao-voice-launcher-1776120138

下载

⬇ 下载 ningyao-voice-launcher v0.1.0（免费）

文件大小: 27.45 KB | 发布时间: 2026-4-15 13:36

v0.1.0 最新 2026-4-15 13:36
Initial public release

相关推荐

s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
返回顶部