From 9a4951760987fe5a4f24f83d503c4d7024215bfb Mon Sep 17 00:00:00 2001
From: Mark Backman <mark@daily.co>
Date: Mon, 20 Apr 2026 19:30:58 -0400
Subject: [PATCH] Add changelog entry for #4341

---
 changelog/4341.added.md | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 changelog/4341.added.md

diff --git a/changelog/4341.added.md b/changelog/4341.added.md
new file mode 100644
index 000000000..9301bcc5f
--- /dev/null
+++ b/changelog/4341.added.md
@@ -0,0 +1 @@
+- Added `XAITTSService` for streaming text-to-speech using xAI's WebSocket TTS endpoint (`wss://api.x.ai/v1/tts`). Streams `text.delta` chunks up and base64 `audio.delta` chunks down on the same connection so audio begins flowing before the full utterance finishes synthesizing; complements the batch-HTTP `XAIHttpTTSService`. Defaults to raw PCM output so `TTSAudioRawFrame` needs no decoding. The `xai` optional extra now pulls in `pipecat-ai[websockets-base]`.