About
We build speech models and voice agents at Lokutor, a small team in Madrid. Our work spans speech recognition, turn taking, noise suppression and speech synthesis, with a separate language model provider. We also build Ito and Oído for the ESP32 S3. We're sharing the models, deployment tradeoffs and what we still need to measure.
Maker History
🎉
Joined Product HuntNovember 1st, 2024
Forums
View more








