From 885b318b04c221fb646b3117a2a238aa92e2b923 Mon Sep 17 00:00:00 2001 From: Paul Kompfner Date: Thu, 15 Jan 2026 15:03:45 -0500 Subject: [PATCH] Fix "bot-llm-text" not firing when using Gemini Live --- .../services/google/gemini_live/llm.py | 23 +++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/src/pipecat/services/google/gemini_live/llm.py b/src/pipecat/services/google/gemini_live/llm.py index 13b5fb18c..f61c9826c 100644 --- a/src/pipecat/services/google/gemini_live/llm.py +++ b/src/pipecat/services/google/gemini_live/llm.py @@ -1710,11 +1710,26 @@ class GeminiLiveLLMService(LLMService): await self.push_frame(TTSStartedFrame()) await self.push_frame(LLMFullResponseStartFrame()) - frame = TTSTextFrame(text=text, aggregated_by=AggregationType.SENTENCE) - # Gemini Live text already includes any necessary inter-chunk spaces - frame.includes_inter_frame_spaces = True + await self._push_output_transcription_text_frames(text) - await self.push_frame(frame) + async def _push_output_transcription_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 Gemini Live 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_msg_grounding_metadata(self, message: LiveServerMessage): """Handle dedicated grounding metadata messages."""