About

Co-founder of Lokutor. We train our own voice models - turn-taking, STT, TTS - to run entirely on CPUs: no GPUs, sub-450ms conversations, and voice agents that can live inside your own infrastructure. Building from Madrid.

Badges

Tastemaker
Tastemaker
Gone streaking 10
Gone streaking 10
Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Forums

Why we trained our entire voice stack from scratch to run on CPUs

We're a small team in Madrid. When we started Lokutor, the usual stack - rented STT, rented LLM, rented TTS, all GPU-bound - didn't work for what our customers needed: unit economics that scale, and data residency for regulated sectors in Spain and LatAm.

So we trained everything ourselves:

- Vela: turn-taking

View more