Openai Whisper
OpenAI Whisper:使用 Whisper 模型进行视频语音识别和转录。
clawhub install openai-whisperCanvas-OS 作为应用平台,可在 OpenClaw Canvas 上构建、存储和运行丰富的可视化应用。
Canvas as an app platform. Build, store, and run rich visual apps on the OpenClaw Canvas.
# 安装 Skill(会下载 SKILL.md 到 .claude/skills/) clawhub install canvas-os # 之后直接对 Claude 说"用 🖥️ Canvas-OS 帮我…"即可
# 同样的安装命令,兼容所有支持 SKILL.md 的 AI 编程工具 clawhub install canvas-os
此 Skill 兼容 OpenClaw 标准。 安装后自动生成 SKILL.md 文件,任何支持 OpenClaw 协议的 AI Agent(Claude Code、Cursor、Windsurf 等)均可直接调用。
需clawhub账户,Canvas平台账号,本地开发无需GPU
file:///path/to/file.html (blocked by Canvas security)CANVAS-LOADING.md for detailed guide + troubleshootingcanvas-inject.py — Formats HTML for direct injection~/.openclaw/workspace/apps/[app-name]/
├── index.html # The UI (self-contained recommended)
├── data.json # Persistent state
└── manifest.json # App metadata
cd ~/.openclaw/workspace/apps/[app-name]
python3 -m http.server [PORT] > /dev/null 2>&1 &
NODE="Your Node Name" # Get from: openclaw nodes status
openclaw nodes canvas navigate --node "$NODE" "http://localhost:[PORT]/"
openclaw nodes canvas eval --node "$NODE" --js "app.setData({...})"
openclaw-canvas:// URL scheme has issues in current OpenClaw versions. Use http://localhost: instead.NODE="Your Node Name"
PORT=9876
APP="my-app"
# 1. Kill any existing server on the port
lsof -ti:$PORT | xargs kill -9 2>/dev/null
# 2. Start server
cd ~/.openclaw/workspace/apps/$APP
python3 -m http.server $PORT > /dev/null 2>&1 &
# 3. Wait for server
sleep 1
# 4. Navigate Canvas
openclaw nodes canvas navigate --node "$NODE" "http://localhost:$PORT/"
# 5. Inject data
openclaw nodes canvas eval --node "$NODE" --js "app.loadData({...})"
# Example using canvas tool
canvas.present(url="about:blank", target=node_name)
html_content = """<!DOCTYPE html>
<html>
<head>
<style>
body { background: #667eea; color: white; padding: 40px; }
.card { background: white; color: #333; padding: 30px; border-radius: 16px; }
</style>
</head>
<body>
<div class="card">
<h1>Your Content Here</h1>
</div>
</body>
</html>"""
# Escape backticks and inject
js_code = f"""document.open();
document.write({html_content});
document.close();"""
canvas.eval(javaScript=js_code, target=node_name)
file:///path/to/file.html) are blocked in Canvas for security. Always use localhost or direct injection.window.app or window.[appname] object:window.app = {
// Update values
setValue: (key, val) => {
document.getElementById(key).textContent = val;
},
// Bulk update
loadData: (data) => { /* render all */ },
// Notifications
notify: (msg) => { /* show toast */ }
};
function sendToAgent(message) {
window.location.href = openclaw://agent?message=${encodeURIComponent(message)};
}
// Button click → agent command
document.getElementById('btn').onclick = () => {
sendToAgent('Refresh my dashboard');
};
dashboard.setRevenue(), dashboard.setProgress(), dashboard.notify()tracker.setItems(), tracker.addItem(), tracker.toggleItem()openclaw nodes canvas a2ui push --node "$NODE" --text "
📊 QUICK STATUS
Revenue: \$500
Users: 100
Done!
"
:root {
--bg-primary: #0a0a0a;
--bg-card: #1a1a2e;
--accent-green: #00d4aa;
--accent-blue: #4a9eff;
--accent-orange: #f59e0b;
--text-primary: #fff;
--text-muted: #888;
--border: #333;
}
window.app.*openclaw nodes canvas navigate, not just openfile:/// URLs for security (sandboxing)canvas eval + document.write() insteadcurl http://localhost:[PORT]/http://localhost: not openclaw-canvas:// (URL scheme has issues)openclaw nodes canvas eval --js "typeof window.app"lsof -ti:[PORT] | xargs kill -9# Example usage in Python
from canvas_inject import inject_html_to_canvas
html = open("my-dashboard.html").read()
commands = inject_html_to_canvas(html, node_name="Your Node")
# Then use canvas tool with these commands
canvas.present(**commands["step1_present"])
canvas.eval(**commands["step2_inject"])
clawhub canvas-os create --name DataDashboard && cd DataDashboard && clawhub canvas-os dev音频转录:使用本地 Whisper(Docker)将音频文件转录为文本,支持 .mp3、.m4a、.ogg、.wav、.webm 等多种格式。
Transcribe audio files to text using local Whisper (Docker). Use when receiving voice messages, audio files (.mp3, .m4a, .ogg, .wav, .webm), or when asked to transcribe audio content.
clawhub install transcribe