voice-uiSelf-evolving voice assistant UI. Talk to your AI, ask it to improve itself, and watch the code update in real-time.
Install via ClawdBot CLI:
clawdbot install yukihamada/voice-ui自己進化型AIアシスタントUI - 音声で会話しながら自分自身を改善できる
cd <workspace>/skills/voice-ui
npm install
./start.sh
ブラウザで http://localhost:8765 を開く
OpenClaw config (~/.openclaw/openclaw.json) に voice agent を追加:
{
"agents": {
"list": [{
"id": "voice",
"name": "Voice Assistant",
"model": { "primary": "anthropic/claude-sonnet-4-5" }
}]
}
}
変更は自動でGitコミットされる。
index.html - メインUIserver.cjs - Node.jsサーバーstart.sh - 起動スクリプトCONTEXT.md - AIへのコンテキスト情報OPENAI_API_KEY - OpenAI API Key(Whisper/TTS用)設定がない場合、OpenClawの設定から自動取得を試みる。
Generated Mar 1, 2026
This skill can be integrated into online learning platforms to provide voice-based tutoring and interactive lessons. Students can verbally ask questions and receive spoken explanations, while instructors can use voice commands to modify the UI for better engagement, such as changing colors or adding visual aids in real-time.
Deploy the voice UI in customer service portals to handle inquiries through natural speech. It allows users to describe issues verbally, and agents can use self-evolution commands to adjust the interface on-the-fly, like enlarging buttons for accessibility or updating response templates based on common queries.
Use this skill in healthcare apps to assist patients with voice-controlled navigation and information retrieval. Medical staff can issue voice commands to customize the UI for different patient needs, such as changing background colors for readability or adding new features for symptom tracking, with changes automatically logged via Git.
Integrate the voice UI into smart home applications to enable residents to control devices through speech. Users can ask the AI to adjust settings, and developers can use self-evolution to modify the interface in real-time, like updating dashboards or adding new control elements based on voice feedback.
Offer the voice UI as a cloud-based service with tiered pricing for different usage levels. Revenue comes from monthly or annual subscriptions, targeting businesses that need customizable voice interfaces without extensive development overhead.
License the skill to large corporations for internal use, such as in training or productivity tools. Revenue is generated through one-time licensing fees or annual contracts, with customization options for specific industry needs like healthcare or education.
Provide a basic version of the voice UI for free to attract individual developers or small teams, then charge for advanced features like enhanced self-evolution commands or priority support. Revenue streams include upgrades and add-ons for professional use cases.
💬 Integration Tip
Ensure the OpenClaw config is properly set up with the voice agent and that the OpenAI API key is available for Whisper and TTS functionality to avoid integration issues.
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.
Local Voice Input/Output for Agents using the AI Voice Agent API.
Transcribe audio files using OpenAI's gpt-4o-mini-transcribe model with vocabulary hints and text replacements. Requires uv (https://docs.astral.sh/uv/).
本地生成 Telegram 语音消息,支持自动清洗、分段与临时文件管理。
Speak responses aloud on macOS using the built-in `say` command when user input indicates Voice Wake/voice recognition (for example, messages starting with "User talked via voice recognition on <device>").
向指定 Telegram 群组发送语音消息