#go
Notes
Writing
The anatomy of time-to-first-audio in a voice agent
From turn-commit to first audio: LLM ~59%, TTS ~28%, my orchestration ~14% — and one first token took 2.9 s. I was tuning the wrong layer.
Giving AI agents a real phone line
50 concurrent phone calls in userspace Go: p50 held at 20.00 ms at every load level — measured, not claimed. The tail is where it gets interesting.
Workshop
Projects
cadence
Provider-agnostic Go engine for low-latency STT→LLM→TTS voice pipelines — streaming engines behind uniform interfaces, swap vendors with a config change. Owns the hot path.
xPhone (Go version)
The embedded telephony data plane for Go. Place and answer calls on any SIP trunk — or be the trunk — with carrier failover, full SIP-signaling visibility, and call audio delivered as PCM frames on a channel, ready for STT or a voice agent. Battle-tested across 500,000+ production calls.