Our Blog

Insights, updates, and deep dives into AI technology and our journey.

Kiri-S2S — The AI That Converses in Khmer Just Like a Real Person
July 23, 2026

Kiri-S2S — The AI That Converses in Khmer Just Like a Real Person

Today, we are excited to introduce Kiri-S2S (Kiri) as a Research Preview! It is the first Real-Time Speech-to-Speech (S2S) AI Model for Khmer, allowing you to speak naturally in Khmer and receive instant spoken responses.

Read More →
Introducing KiriTTS: Our New Text-to-Speech Model
April 12, 2026

Introducing KiriTTS: Our New Text-to-Speech Model

Today we are releasing KiriTTS — a multilingual, expressive Text-to-Speech model built for real-world applications. Here is what it can do and why we built it.

Read More →
Building Text Detection: Inside Kiri OCR's DB Implementation
January 29, 2026

Building Text Detection: Inside Kiri OCR's DB Implementation

When building Kiri OCR, we faced a huge challenge: getting the computer to 'see' where the text is on a page. This is the story of how we built our text detector using a method called DB (Differentiable Binarization).

Read More →