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

Merge pull request #1824 from pipecat-ai/mb/gemini-live-transcribe-user-audio

Browse Source 
Update GeminiMultimodalLiveLLMService to use Gemini's user transcription
This commit is contained in:
Mark Backman
2025-05-16 22:51:04 -04:00
committed by GitHub
parent 88e472b3f1 fac6f526f7
commit deb43df0a4
10 changed files with 131 additions and 154 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/foundational/26-gemini-multimodal-live.py
View File

@@ -53,7 +53,6 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespac
api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction=system_instruction,
voice_id="Puck", # Aoede, Charon, Fenrir, Kore, Puck
transcribe_user_audio=True,
)
# Build the pipeline

1
examples/foundational/26a-gemini-multimodal-live-transcription.py
View File

@@ -47,7 +47,6 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespac
api_key=os.getenv("GOOGLE_API_KEY"),
voice_id="Aoede", # Puck, Charon, Kore, Fenrir, Aoede
# system_instruction="Talk like a pirate."
transcribe_user_audio=True,
# inference_on_context_initialization=False,
)

1
examples/foundational/26b-gemini-multimodal-live-function-calling.py
View File

@@ -89,7 +89,6 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespac
llm = GeminiMultimodalLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction=system_instruction,
transcribe_user_audio=True,
tools=tools,
)

1
examples/foundational/26c-gemini-multimodal-live-video.py
View File

@@ -51,7 +51,6 @@ async def main():
api_key=os.getenv("GOOGLE_API_KEY"),
voice_id="Aoede", # Puck, Charon, Kore, Fenrir, Aoede
# system_instruction="Talk like a pirate."
transcribe_user_audio=True,
# inference_on_context_initialization=False,
)

1
examples/foundational/26d-gemini-multimodal-live-text.py
View File

@@ -59,7 +59,6 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespac
llm = GeminiMultimodalLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
transcribe_user_audio=True,
system_instruction=SYSTEM_INSTRUCTION,
tools=[{"google_search": {}}, {"code_execution": {}}],
params=InputParams(modalities=GeminiMultimodalModalities.TEXT),

1
examples/foundational/26e-gemini-multimodal-google-search.py
View File

@@ -58,7 +58,6 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespac
llm = GeminiMultimodalLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
voice_id="Puck", # Aoede, Charon, Fenrir, Kore, Puck
transcribe_user_audio=True,
system_instruction=system_instruction,
tools=tools,
)