# Sakana AI — KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI

- Company: Sakana AI (sakana.ai)
- Announced: 2026-04-28T15:00:00+00:00
- Category: research-paper
- Subject: Sakana models
- Models affected: KAME
- Source: https://sakana.ai/kame-icassp-2026
- Record: https://forck.live/items/4685-kame-tandem-architecture-for-enhancing-knowledge-in-real-time-speech-to-speech

Sakana AI introduces KAME, a tandem architecture for real-time speech-to-speech conversational AI that uses a fast speech model and an asynchronous backend LLM to enable 'speak while thinking'.

## Evidence

Verbatim from https://sakana.ai/kame-icassp-2026:

> We’re excited to introduce KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI, accepted at ICASSP2026!

---

Record: https://forck.live/items/4685-kame-tandem-architecture-for-enhancing-knowledge-in-real-time-speech-to-speech
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md