agents
agents copied to clipboard
livekit
Build real-time multimodal AI applications 🤖🎙️📹
For LiveKit agent plugin versions livekit-agents==0.8.8, we get room metadata in async def request_fnc(req: JobRequest) -> None: in req.room.metadata as value what we set while creating room, but in version...
Do you have any plan to support, - Nvidia Riva [STT](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/asr/asr-overview.html) - Nvidia Riva [TTS](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/tts/tts-overview.html) Thanks
Can you provide an example of how can I run the agents in uvicorn app? I am using fastapi on the backend and when a post request is made, I...
I have implemented the ability to send STT transcripts to the LLM along with detailed word-level information.
When using the google STT, unlike deepgram STT the run loop doesn't gracefully terminate when agent disconnected: ### Error ``` 2024-10-07 10:55:10,339 - WARNING livekit.plugins.google - google stt connection failed,...
Agent state would update to listening when the user started speaking, even if the agent was still speaking. This also fixes some bugs where uninterruptable speech would actually be interrupted.
## Issue Solved: #855 ## Changes Made - Added `CODE_OF_CONDUCT.md` in the root directory. - Defined expectations for behavior, procedures for reporting issues, and consequences for violations. ## Sample Screenshot...
**Please describe your suggestion, and the problem it'd solve.** I suggest creating a Code of Conduct for our project. This document would help establish clear expectations for behavior within our...
**Description** I'm encountering a `TypeError` in the `VoicePipelineAgent` when using OpenAI's STT service to process the final transcript. It appears that the `_transcribed_text` attribute is being concatenated with a `NoneType`...
