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

feat(gemini): enable audio transcription in live text example

Browse Source 
Add options to transcribe both user and model audio during the GeminiMultimodalLiveLLMService setup in the 26d-gemini-multimodal-live-text.py example.
This commit is contained in:
Mert Sefa AKGUN
2025-01-09 15:38:33 +03:00
parent 7634058f97
commit 6664c492ac
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/foundational/26d-gemini-multimodal-live-text.py
View File

@@ -56,6 +56,8 @@ async def main():
llm = GeminiMultimodalLiveLLMService( llm = GeminiMultimodalLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"), api_key=os.getenv("GOOGLE_API_KEY"),
# system_instruction="Talk like a pirate." # system_instruction="Talk like a pirate."
transcribe_user_audio=True,
transcribe_model_audio=True,
) )
llm.set_model_modalities( llm.set_model_modalities(
GeminiMultimodalModalities.TEXT GeminiMultimodalModalities.TEXT