| --- |
| language: |
| - km |
| - en |
| tags: |
| - speech-to-speech |
| - voice-ai |
| - khmer |
| - conversational |
| pipeline_tag: audio-to-audio |
| --- |
| |
| # Kiri-S2S β Real-Time Khmer Speech-to-Speech AI |
|
|
| **Kiri (ααΈααΈ)** is an end-to-end, real-time speech-to-speech conversational AI model built **Khmer-first** by [Blizzer](https://blizzer.tech). |
|
|
| Speak to it in Khmer and it talks back in a natural voice in under a second β streaming audio while the rest of the reply is still being generated. It also converses in English and supports live translation. |
|
|
| *The name "Kiri" comes from the Khmer word for "mountain" (ααΈααΈ).* |
|
|
| π **Try the Live Demo:** [s2s.blizzer.tech](https://s2s.blizzer.tech/) |
| π **Read the Launch Post:** [English Blog](https://www.blizzer.tech/blog/introducing-kiri-s2s) | [α’αααααααΆααΆααΆααααα (Khmer)](https://www.blizzer.tech/blog/introducing-kiri-s2s?locale=km) |
|
|
| --- |
|
|
| ## Key Capabilities |
|
|
| - **Speech-to-Speech (S2S):** Understands raw audio input directly and generates spoken responses natively without separate intermediate conversion steps. |
| - **Real-Time Streaming:** Responds in **<1 second** regardless of reply length; starts speaking while processing continues. |
| - **Khmer-First & Bilingual:** Native Khmer and English support, seamlessly switching languages or translating live on request. |
| - **4 Built-in Native Voices:** Select between **Bosba**, **Borey**, **Setha**, and **Maly**. |
| - **Live-Call Ready:** Designed for real-time streaming voice interactions with barge-in support (interrupt mid-sentence). |
|
|
| --- |
|
|
| ## Model Overview |
|
|
| - **Model Size:** 2.04 Billion Parameters |
| - **Architecture:** End-to-End Native Speech-to-Speech Neural Architecture |
| - **Tokenizer Efficiency:** Extended with 4,000 native Khmer tokens (**β80% token processing cost for Khmer** compared to standard multilingual models). |
|
|
| --- |
|
|
| ## Current Limitations (Research Preview) |
|
|
| - **Research Preview:** May occasionally make factual errors, misinterpret background noise, or produce unnatural phrasing. |
| - **Language Scope:** Optimized for Khmer and English only. |
| - **Voice Options:** Fixed to the four built-in speakers. |
| - **Non-Professional Advice:** Not intended for medical, legal, or financial decision-making. |
|
|
| --- |
|
|
| ## About Blizzer |
|
|
| Developed by **Blizzer**, a Cambodian AI startup dedicated to building voice AI technology that natively serves Khmer speakers. |
|
|
| - ποΈ **Live Demo:** [https://s2s.blizzer.tech/](https://s2s.blizzer.tech/) |
| - π **English Blog:** [blizzer.tech/blog/introducing-kiri-s2s](https://www.blizzer.tech/blog/introducing-kiri-s2s) |
| - π°π **Khmer Blog:** [blizzer.tech/blog/introducing-kiri-s2s?locale=km](https://www.blizzer.tech/blog/introducing-kiri-s2s?locale=km) |
| - π **Company Website:** [blizzer.tech](https://blizzer.tech) |
