Some customers use the speaker's small language model with better knowledge bases and memory than GPT-4 or GPT-4.1, according to the speaker.

“pair our models with our own like small language model it's called electron we fine-tune one of those to make it work for real-time voice use cases and see a lot of folks using that with better knowledge basis memory etc over gpt4 or 4.1 you know the popular real-time models just a from a cost perspective it's lower b from latency perspective it's like way lower”