通过 AirPods 和你的 AI 智能体对话 — 50 行代码打造 Siri 语音管线

const express = require('express');
const { execSync } = require('child_process');
const fs = require('fs');

const app = express();
app.use(express.json());

const AUTH_TOKEN = process.env.AUTH_TOKEN || 'your-secret-token';
const AI_URL = process.env.AI_URL || 'https://api.openai.com/v1/chat/completions';
const AI_TOKEN = process.env.AI_TOKEN || 'your-ai-api-key';
const AI_MODEL = process.env.AI_MODEL || 'gpt-4o';
const TTS_VOICE = process.env.TTS_VOICE || 'en-US-AndrewNeural';

app.post('/voice', async (req, res) => {
  try {
    const token = (req.headers['authorization'] || '')
      .replace('Bearer ', '').trim();
    if (token !== AUTH_TOKEN)
      return res.status(401).json({ error: 'unauthorized' });

    const text = req.body?.text;
    if (!text)
      return res.status(400).json({ error: 'no text' });

    // 1. Ask your AI agent
    const r = await fetch(AI_URL, {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'Authorization': 'Bearer ' + AI_TOKEN,
      },
      body: JSON.stringify({
        model: AI_MODEL,
        max_tokens: 300,
        user: 'voice-user', // persistent session across calls
        messages: [
          {
            role: 'system',
            content: 'User is speaking via voice. Keep responses '
              + 'SHORT (2-3 sentences). Spoken aloud. '
              + 'No markdown, bullets, code, or URLs.'
          },
          { role: 'user', content: text }
        ],
      }),
    });

    const data = await r.json();
    let reply = data.choices?.[0]?.message?.content || 'No response.';

    // 2. Convert to speech (free!)
    const tmp = '/tmp/voice-' + Date.now() + '.mp3';
    execSync(
      `edge-tts --voice ${TTS_VOICE} ` +
      `--text '${reply.replace(/'/g, "'\\''")}' ` +
      `--write-media ${tmp} 2>/dev/null`,
      { timeout: 15000 }
    );

    const audio = fs.readFileSync(tmp);
    fs.unlinkSync(tmp);

    res.set('Content-Type', 'audio/mpeg');
    res.send(audio);
  } catch (err) {
    if (!res.headersSent)
      res.status(500).json({ error: err.message });
  }
});

app.get('/health', (req, res) => res.json({ ok: true }));

app.listen(3456, () => console.log('Voice API on :3456'));

npm init -y
npm install express
pip install edge-tts
node server.js

export AI_URL="http://localhost:11434/v1/chat/completions"  # ollama example
export AI_TOKEN="not-needed-for-local"
export AI_MODEL="llama3"

User is speaking via voice. Keep responses SHORT (2-3 sentences).
Spoken aloud. No markdown, bullets, code, or URLs.

pip install edge-tts

# list all voices
edge-tts --list-voices

# generate speech
edge-tts --voice en-US-AndrewNeural \
  --text "Hello from your AI assistant" \
  --write-media output.mp3

# install
curl -L https://github.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-amd64 \
  -o /usr/local/bin/cloudflared
chmod +x /usr/local/bin/cloudflared

# run
cloudflared tunnel --url http://localhost:3456

openclaw config patch '{
  "http": {
    "endpoints": {
      "chatCompletions": { "enabled": true }
    }
  }
}'

cat ~/.openclaw/gateway.json | jq -r '.auth.bearerTokens[0]'

export AI_URL="http://127.0.0.1:18789/v1/chat/completions"
export AI_TOKEN="your-gateway-bearer-token"
export AI_MODEL="openclaw:main"
export AUTH_TOKEN="pick-a-secret-for-siri"
export TTS_VOICE="en-US-AndrewNeural"

node server.js &
cloudflared tunnel --url http://localhost:3456

"Siri，助手"
    → iPhone 转录语音
    → POST 到你的服务器
    → 服务器询问你的 AI 智能体
    → 智能体回复（2-3 句话）
    → Edge TTS 转换为 MP3
    → MP3 通过 AirPods 播放
    ← 总共 3-5 秒