agents
agents copied to clipboard
A powerful framework for building realtime voice AI agents π€ποΈπΉ
This should close #4407 Tested with the following setup. ```python } session = AgentSession( ... llm=google.LLM( model="gemini-2.5-flash", vertexai=True, location="global", # retrieval_config=types.RetrievalConfig( # lat_lng=types.LatLng(latitude=53.350140, longitude=-6.266155) # ), # or retrieval_config={ "lat_lng":...
Tested the ambiguous ones: "gemini-2.0-flash-exp" and "gemini-live-2.5-flash-preview-native-audio". Both still work with the right setting, but are not mentioned in any official docs or change logs.
- Add batch recognition flag in STT capabilities - Added manual workflow to test a PR/branch/revision - Updated tests to support all STT vendors except two of them: ```python #...
This should close #4413 What happened: - VAD received audio frames, changing user stage to speaking; - Uninterruptible speech created, discarding audio frames for both STT and VAD. User state...
### Bug Description ### Error message ``` websockets.exceptions.ConnectionClosedError: received 1007 (invalid frame payload data) Cannot extract voices from a non-audio request. ``` ### Code to reproduce ```python from livekit.agents import...
### Bug Description When using VideoAvatars with multiple agents under a single AgentSession, the audio input/output (QueueAudioOutput) is initialized once when the avatar starts. Currently, thereβs no way to reset...
### Bug Description If the agent has a `self.session.say` inside of a tool call, and you interrupt right before it. The agent will be stuck and unable to respond. All...
### Bug Description https://docs.livekit.io/deploy/observability/data/#save-conversation-history-example https://docs.livekit.io/deploy/observability/data/#session-reports I want to be able to add the whole session report as a span attribute to the root span. I am unable to do it...