From f2271ae84538a57cc20e84fc44d0f5a0bea50085 Mon Sep 17 00:00:00 2001
From: Nikhil Jangid <161968345+nikhiljangid120@users.noreply.github.com>
Date: Sat, 3 Oct 2026 01:33:25 -0500
Subject: [PATCH] docs: note profile engine default fix

Document the generation engine precedence correction.
---
 CHANGELOG.md | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 0b03f5e4..d1d59953 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,8 +7,14 @@
 
 ## [Unreleased]
 
+### Fixed
+
+- Voice generation requests that omit `engine` now honor the selected profile's
+  configured engine instead of silently defaulting to Qwen.
+
 ### Linux
 
+
 - **ROCm setup works on Linux AMD systems.** Docker ROCm builds now keep PyTorch
   on the ROCm wheel index during dependency installation, so later installs do
   not replace it with CUDA wheels. The ROCm compose overlay no longer assumes