wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #975 from imsakg/main

Browse Source 
fix(gemini): prevent non-audio modality processing
This commit is contained in:
Mark Backman
2025-01-22 09:03:18 -05:00
committed by GitHub
parent 0d79a9eaa6 14e5419913
commit 0ba60c9e28
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/pipecat/services/gemini_multimodal_live/gemini.py
View File

@@ -288,6 +288,10 @@ class GeminiMultimodalLiveLLMService(LLMService):
) )
async def _handle_transcribe_model_audio(self, audio, context): async def _handle_transcribe_model_audio(self, audio, context):
# Early return if modalities are not set to audio.
if self._settings["modalities"] != GeminiMultimodalModalities.AUDIO:
return
text = await self._transcribe_audio(audio, context) text = await self._transcribe_audio(audio, context)
logger.debug(f"[Transcription:model] {text}") logger.debug(f"[Transcription:model] {text}")
# We add user messages directly to the context. We don't do that for assistant messages, # We add user messages directly to the context. We don't do that for assistant messages,