diff --git a/changelog/3814.added.md b/changelog/3814.added.md
new file mode 100644
index 000000000..b6b2ebbf8
--- /dev/null
+++ b/changelog/3814.added.md
@@ -0,0 +1 @@
+- Added `on_audio_context_interrupted()` and `on_audio_context_completed()` callbacks to `AudioContextTTSService`. Subclasses can override these to perform provider-specific cleanup instead of overriding `_handle_interruption()`.
diff --git a/changelog/3814.fixed.md b/changelog/3814.fixed.md
new file mode 100644
index 000000000..ecd4871f6
--- /dev/null
+++ b/changelog/3814.fixed.md
@@ -0,0 +1 @@
+- Fixed an issue where `AudioContextTTSService`-based providers (AsyncAI, ElevenLabs, Inworld, Rime) did not close or clean up their server-side audio contexts after normal speech completion, only on interruption.