Default cold · no caches warm
2135over the 1500 ms gate
Optimized warm · all speculation hits
625passes with margin
STT silence
Middleware
RAG
Memory
LLM TTFT
Tool dispatch
LLM continuation
TTS formatter
Cartesia first audio
TX pacer
Where the speculation saves time
RAG retrieval50 → 5 ms (cache hit)
Memory load20 → 5 ms (cache hit)
LLM TTFT900 → 50 ms (the big one · ~95% hit in clean rooms)
Tool dispatch300 → 50 ms (pre-dispatched read-only tool)
LLM continuation250 → 150 ms (faster post-tool turn)
TTS formatter300 → 50 ms (Haiku formatter pre-warmed)