perf(say-server): add initial delay before polling

Add 150ms delay before first poll to give TTS model time to generate
the first audio chunk. This reduces unnecessary polling and server load.

Current backoff after that:
- 30ms if chunks received (keep streaming fast)
- 80ms if no chunks (wait longer for generation)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

Author: ochafik

examples/say-server/server.py

@@ -922,6 +922,8 @@ def generate_sync():
         const app = appRef.current;
         if (isPollingRef.current || !app) return;
         isPollingRef.current = true;
+        // Initial delay to let TTS generate first chunk (reduces unnecessary polls)
+        await new Promise(r => setTimeout(r, 150));
         while (queueIdRef.current) {
           try {
             const result = await app.callServerTool({ name: "poll_tts_audio", arguments: { queue_id: queueIdRef.current } });