Backed by Y Combinator
Engineering notes from every layer of the on-device stack
VoiceFebruary 24, 2026
We added hybrid retrieval (BM25 + vector search) to our on-device voice pipeline. Retrieval adds less than 4ms. The real cost is LLM prefill — but word-level flushing absorbs it. Sub-200ms first-audio on 5,016 chunks with zero cloud dependencies.
VoiceFebruary 22, 2026
FastVoice achieves 63ms first-audio latency — well under the 200ms perceptual threshold — by composing STT, LLM, and TTS into a single C++ pipeline on Apple Silicon. No cloud. No network. Just speed.
RunAnywhere Labs
We build the engines, SDKs, and agents that put inference where latency, cost, and privacy want it — on-prem, cloud, edge, or in between.
Research
Legal
