guidesFebruary 16, 2026· 4 min read

Cache the Gemini SDK in your voice assistant with Crowkis

Building voice assistants on the Gemini SDK? Add a semantic cache so latency-sensitive, repetitive spoken queries stop costing full price.

Voice assistants built on the Gemini SDK share one problem: latency-sensitive, repetitive spoken queries. Each repeat is a full-price the Gemini SDK call for an answer you already have.

Put a semantic cache in front. Point the Gemini SDK's base URL at the Crowkis OpenAI-compatible gateway, or wrap the call in get-or-compute, and reworded repeats are served from cache, no rewrite of your voice assistants logic.

the Gemini SDK + Crowkis

base_url = "http://127.0.0.1:6380/v1"   # Crowkis gateway, semantic cache in front

In plain words: The voice assistants keep working exactly as before; the repeats just stop hitting the model.

On repetitive traffic this cuts costs up to 60-70% on repetitive workloads, and every hit carries a confidence score so reuse stays safe. Drop it in over RESP, gRPC, REST, or MCP, no rewrite required.