From 5de80a60d4812eed1816141d9e46c5a32d12dca4 Mon Sep 17 00:00:00 2001
From: Paul Kompfner <paul@daily.co>
Date: Thu, 15 Jan 2026 15:30:00 -0500
Subject: [PATCH] Fix "bot-llm-text" not firing when using Grok Realtime

---
 src/pipecat/services/grok/realtime/llm.py | 24 ++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/src/pipecat/services/grok/realtime/llm.py b/src/pipecat/services/grok/realtime/llm.py
index bcd701cd3..5e368b62b 100644
--- a/src/pipecat/services/grok/realtime/llm.py
+++ b/src/pipecat/services/grok/realtime/llm.py
@@ -33,6 +33,7 @@ from pipecat.frames.frames import (
     LLMFullResponseStartFrame,
     LLMMessagesAppendFrame,
     LLMSetToolsFrame,
+    LLMTextFrame,
     LLMUpdateSettingsFrame,
     StartFrame,
     TranscriptionFrame,
@@ -619,9 +620,26 @@ class GrokRealtimeLLMService(LLMService):
     async def _handle_evt_audio_transcript_delta(self, evt):
         """Handle audio transcript delta event."""
         if evt.delta:
-            frame = TTSTextFrame(evt.delta, aggregated_by=AggregationType.SENTENCE)
-            frame.includes_inter_frame_spaces = True
-            await self.push_frame(frame)
+            await self._push_output_transcript_text_frames(evt.delta)
+
+    async def _push_output_transcript_text_frames(self, text: str):
+        # In a typical "cascade" LLM + TTS setup, LLMTextFrames would not
+        # proceed beyond the TTS service. Therefore, since a speech-to-speech
+        # service like Grok Realtime combines both LLM and TTS functionality,
+        # you might think we wouldn't need to push LLMTextFrames at all.
+        # However, RTVI relies on LLMTextFrames being pushed to trigger its
+        # "bot-llm-text" event. So here we push an LLMTextFrame, too, but avoid
+        # appending it to context to avoid context message duplication.
+
+        # Push LLMTextFrame
+        llm_text_frame = LLMTextFrame(text)
+        llm_text_frame.append_to_context = False
+        await self.push_frame(llm_text_frame)
+
+        # Push TTSTextFrame
+        tts_text_frame = TTSTextFrame(text, aggregated_by=AggregationType.SENTENCE)
+        tts_text_frame.includes_inter_frame_spaces = True
+        await self.push_frame(tts_text_frame)
 
     async def _handle_evt_function_call_arguments_done(self, evt):
         """Handle function call arguments done event."""