From acd0660f66ccecaabf3089480045faba0c37a586 Mon Sep 17 00:00:00 2001
From: Mark Backman <mark@daily.co>
Date: Fri, 14 Mar 2025 14:00:38 -0400
Subject: [PATCH] Update GeminiMultimodalLiveLLMService to work with the
 TranscriptProcessor

---
 CHANGELOG.md                                          | 3 ++-
 src/pipecat/services/gemini_multimodal_live/gemini.py | 2 ++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 596a3e1e0..7376603c1 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -93,7 +93,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Updated `TranscriptProcessor` to support text output from
   `OpenAIRealtimeBetaLLMService`.
 
-- `OpenAIRealtimeBetaLLMService` now pushes a `TTSTextFrame`.
+- `OpenAIRealtimeBetaLLMService` and `GeminiMultimodalLiveLLMService` now push
+  a `TTSTextFrame`.
 
 - Updated the default mode for `CartesiaTTSService` and
   `CartesiaHttpTTSService` to `sonic-2`.
diff --git a/src/pipecat/services/gemini_multimodal_live/gemini.py b/src/pipecat/services/gemini_multimodal_live/gemini.py
index ef49df329..5fe8a792b 100644
--- a/src/pipecat/services/gemini_multimodal_live/gemini.py
+++ b/src/pipecat/services/gemini_multimodal_live/gemini.py
@@ -38,6 +38,7 @@ from pipecat.frames.frames import (
     TTSAudioRawFrame,
     TTSStartedFrame,
     TTSStoppedFrame,
+    TTSTextFrame,
     UserStartedSpeakingFrame,
     UserStoppedSpeakingFrame,
 )
@@ -312,6 +313,7 @@ class GeminiMultimodalLiveLLMService(LLMService):
         # context.add_message({"role": "assistant", "content": [{"type": "text", "text": text}]})
         await self.push_frame(LLMFullResponseStartFrame())
         await self.push_frame(LLMTextFrame(text=text))
+        await self.push_frame(TTSTextFrame(text=text))
         await self.push_frame(LLMFullResponseEndFrame())
 
     async def _transcribe_audio(self, audio, context):