Ningyao Voice Launcher

Install the bundled launcher into a user-chosen folder, then configure .env and run it.

Workflow

1. 1. Copy assets/voice-chat-local into the target folder.
2. Install dependencies with npm install in the copied folder.
3. Copy .env.example to .env and fill in OPENAI_API_KEY.
4. Start with start-voice-chat.cmd or start-voice-chat-bg.cmd.

Bundled Files

• - assets/voice-chat-local: Browser voice chat app template.
• INLINECODE9: Windows installer/copy helper.

Windows Install

Run:

CODEBLOCK0

The installer copies the template, skips .env, and can optionally run npm install.

Configuration

Set these in .env:

• - OPENAI_API_KEY: required
• INLINECODE14: optional API-compatible endpoint
• INLINECODE15: text + vision capable model if screen analysis is needed
• INLINECODE16: request timeout
• INLINECODE17: local port
• INLINECODE18: persona prompt

Notes

• - Prefer Chrome or Edge for browser speech recognition and speech synthesis.
• The terminal panel is intentionally restricted to a small whitelist.
• If screen analysis is enabled, choose a model that supports image input.