From ea0be4d39c8c6bdc32595d79ba7b6c04cbbdccad Mon Sep 17 00:00:00 2001
From: filipi87 <filipi87@gmail.com>
Date: Thu, 9 Apr 2026 15:25:06 -0300
Subject: [PATCH] Changelog for the elevenlabs fix.

---
 changelog/4265.fixed.md | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 changelog/4265.fixed.md

diff --git a/changelog/4265.fixed.md b/changelog/4265.fixed.md
new file mode 100644
index 000000000..19f7db78c
--- /dev/null
+++ b/changelog/4265.fixed.md
@@ -0,0 +1 @@
+- Fixed `ElevenLabsTTSService` incorrectly enabling `auto_mode` when using `TextAggregationMode.TOKEN`. Auto mode disables server-side buffering and is designed for complete sentences — enabling it with token streaming degraded speech quality. The default is now derived automatically from the aggregation strategy: `auto_mode=True` for `SENTENCE`, `auto_mode=False` for `TOKEN`. Callers can still override by passing `auto_mode` explicitly.