#voice-ai
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.
Projects
Vocito
Dictation that types for you — push-to-talk voice typing for macOS. Talk naturally, false starts and all; Vocito types the sentence you meant, formatted for wherever you're writing. Private beta.
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.
claude-voice
Give Claude Code a voice — selective, tasteful spoken summaries and attention cues. Quiet by default.
tts-bridge
TTS APIs speak HTTP. Voice apps speak WebSocket. This bridges the gap.