From c1908a549fc62732d21a7afe3c1ed0c68d6d7fc7 Mon Sep 17 00:00:00 2001 From: Chad Auld Date: Sun, 16 Nov 2025 12:36:35 -0700 Subject: [PATCH] Add important disclaimer about LLM model impact on performance - Clarify that integration provides search, but LLM determines accuracy/speed - Recommend qwen3:4b as good starting point for local voice pipelines - Link to Performance section for optimization guidance --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index f6680c4..27798e5 100644 --- a/README.md +++ b/README.md @@ -28,6 +28,8 @@ Before using this integration, you need: **Use both together:** Many users run Music Assistant for UI/management and this integration for voice control via custom conversation agents. +> **⚠️ Important:** This integration provides the search functionality - your conversation agent's LLM model and hardware determine the actual voice command accuracy and response time. For local voice pipelines, qwen3:4b is a pretty good starting point. See [Performance](#performance) for optimization guidance. + ## The Problem Want to control Spotify with your voice in Home Assistant? You'll quickly hit these issues: